CN115170210A - Reception method at building, electronic device and readable storage medium - Google Patents
Reception method at building, electronic device and readable storage medium Download PDFInfo
- Publication number
- CN115170210A CN115170210A CN202211081898.0A CN202211081898A CN115170210A CN 115170210 A CN115170210 A CN 115170210A CN 202211081898 A CN202211081898 A CN 202211081898A CN 115170210 A CN115170210 A CN 115170210A
- Authority
- CN
- China
- Prior art keywords
- information
- consultation
- preset
- intention
- building
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000000605 extraction Methods 0.000 claims abstract description 79
- 238000012549 training Methods 0.000 claims abstract description 65
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 238000013145 classification model Methods 0.000 claims description 51
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000009223 counseling Methods 0.000 claims 1
- 239000000126 substance Substances 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 13
- 239000011159 matrix material Substances 0.000 description 9
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000013507 mapping Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 239000013598 vector Substances 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 241000699670 Mus sp. Species 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a reception method, electronic equipment and a readable storage medium for a building, which are applied to the field of real estate, wherein the reception method for the building comprises the following steps: acquiring consultation information of a target client in a building, and extracting information semantic features of the consultation information through a preset semantic extraction model, wherein the preset semantic extraction model is obtained on the basis of contrast learning training and timing increment learning optimization; matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer; and replying the consultation information according to the matching result. The technical problem of the customer of selling the building department receive the inefficiency has been solved to this application.
Description
Technical Field
The present application relates to the field of real estate, and in particular, to a reception method, an electronic device, and a readable storage medium for a building.
Background
With the rapid development of science and technology, the real estate industry is developed more and more mature, at present, when a real estate company sells a floor, the problem of a client is solved at a building selling place usually by a placement consultant, and when the passenger flow volume is large, the situation that all clients cannot be received may occur due to less placement consultants, so that the receiving efficiency of the client at the building selling place is low.
Disclosure of Invention
The present application mainly aims to provide a reception method, an electronic device and a readable storage medium for a building, and aims to solve the technical problem of low customer reception efficiency in a building in the prior art.
In order to achieve the above object, the present application provides a reception method for a building, which is applied to a reception device for a building, and the reception method for a building comprises:
acquiring consultation information of a target client in a building, and extracting information semantic features of the consultation information through a preset semantic extraction model, wherein the preset semantic extraction model is obtained based on contrast learning training and timing increment learning optimization;
matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer;
and replying the consultation information according to the matching result.
In order to achieve the above object, the present application further provides a reception device for a building, where the reception device is applied to a reception device for a building, and the reception device for a building comprises:
the system comprises an extraction module, a query module and a query module, wherein the extraction module is used for acquiring consultation information of a target client in a building and extracting information semantic features of the consultation information through a preset semantic extraction model, and the preset semantic extraction model is obtained based on contrast learning training and timing increment learning optimization;
the matching module is used for matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer;
and the reply module is used for replying the consultation information according to the matching result.
The present application further provides an electronic device, the electronic device including: a memory, a processor, and a program of a hospitality method at the building stored on the memory and executable on the processor, the program of a hospitality method at a building when executed by the processor, implementing the steps of a hospitality method at a building as described above.
The present application also provides a computer-readable storage medium having stored thereon a program for implementing a method for hospitality at a building, which when executed by a processor implements the steps of the method for hospitality at a building as described above.
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the reception method at a building as described above.
Compared with a method for solving a problem of a client at a building through a public consultant, the method for receiving the problem of the client at the building is characterized in that consultation information of the target client at the building is collected, and information semantic features of the consultation information are extracted through a preset semantic extraction model, wherein the preset semantic extraction model is obtained on the basis of contrast learning training and timing increment learning optimization; matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer; according to the matching result, the consultation information is responded, the response result is matched according to the information semantic features of the extracted consultation information and the information semantic features, so that the automation of the customer at the building place for reception is realized, the technical defect that all the customers cannot be received due to less business consultants at the peak of the customer flow when the customer problem is solved at the building place by the business consultants is avoided, and the customer reception efficiency at the building place is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive labor.
FIG. 1 is a schematic flow chart of a first embodiment of a reception method at a building location of the present application;
FIG. 2 is a schematic view of an application scenario in the reception method of the building sales department of the present application;
FIG. 3 is a schematic flow chart illustrating a second embodiment of a reception method at a building for the present application;
FIG. 4 is a schematic structural diagram of a device involved in the reception method at a building;
fig. 5 is a schematic structural diagram of a hardware operating environment related to a reception method at a building according to an embodiment of the present application.
The implementation of the objectives, functional features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments of the present application are described in detail below with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example one
In a first embodiment of the method for building sales reception according to the present application, with reference to fig. 1, the method for building sales reception includes:
step S10, acquiring consultation information of a target client in a building, and extracting information semantic features of the consultation information through a preset semantic extraction model, wherein the preset semantic extraction model is obtained based on contrast learning training and timing increment learning optimization;
in this embodiment, it should be noted that the information semantic features are used for representing the semantics of the advisory information.
Exemplarily, step S10 includes: acquiring voice information of a target client in a building, and acquiring consultation information of the target client by recognizing the voice information, or acquiring keying-in text information of the target client in the building, and taking the keying-in text information as the consultation information; and mapping the consultation information into information semantic features through a preset semantic extraction model.
In step S10, before the step of extracting the information semantic features of the advisory information by using the preset semantic extraction model, the method further includes:
step D10, obtaining the length of the information byte of the consultation information;
step D20, judging whether the length of the information byte is larger than a preset byte threshold value or not;
step D30, if yes, executing the following steps: extracting information semantic features of the consultation information through a preset semantic extraction model;
step D40, if not, extracting the information semantic features of the consultation information through singular value decomposition, and executing the steps of: and matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result.
In this embodiment, it should be noted that the preset byte threshold is a preset critical value for determining the length of the information byte with a larger information amount of the advisory information.
Exemplarily, the steps D10 to D40 include: acquiring the length of the information byte of the consultation information, judging whether the length of the information byte is greater than a preset byte threshold value, and if the length of the information byte is greater than the preset byte threshold value, executing the following steps: extracting information semantic features of the consultation information through a preset semantic extraction model; if the length of the information byte is not greater than a preset byte threshold value, extracting information semantic features of the consultation information through singular value decomposition, and executing the following steps: and matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result.
Optionally, the step of extracting the information semantic features of the advisory information through singular value decomposition may be: acquiring information key words in the consultation information and the occurrence frequency of each information key word, and constructing a consultation information matrix corresponding to the consultation information according to the information key words and the frequency corresponding to the information key words; singular value decomposition is carried out on the consultation information matrix to obtain a left singular value matrix, a right singular value matrix and a diagonal matrix, and information semantic features corresponding to the information key words are obtained by mapping each information key word to a first space point-multiplied by the left singular value matrix and the diagonal matrix; and mapping each information key word to a second space point-multiplied by the right singular value matrix and the diagonal matrix to obtain the information semantic features corresponding to the consultation information.
It can be understood that the preset semantic extraction model has high feature extraction accuracy but low feature extraction efficiency, the singular value decomposition has low feature extraction accuracy for content complex information but high feature extraction efficiency, and the feature extraction method is selected according to the information byte length of the advisory information, so that the feature extraction accuracy and the feature extraction efficiency can be balanced.
In step S10, before the step of extracting information semantic features of the advisory information by using a preset semantic extraction model, the step of obtaining the preset semantic extraction model based on contrast learning training further includes:
step E10, obtaining historical consultation data of clients in a building selling scene, and determining a training sample set of a preset semantic extraction model according to the historical consultation data;
step E20, constructing an enhanced sample set of the training sample set, wherein the enhanced sample set comprises a standard sample, a positive sample and a negative sample, the standard sample is standard consulting information corresponding to each consulting intention, the positive sample is related consulting information corresponding to each consulting sentence pattern with similar semantics to the consulting intention, and the negative sample is unrelated consulting information corresponding to each consulting sentence pattern without similar semantics to the consulting intention;
and E30, carrying out iterative optimization on the preset semantic extraction model to be trained according to the enhanced sample set to obtain the preset semantic extraction model.
Exemplarily, the steps E10 to E30 include: respectively inputting each standard sample, each positive sample and each negative sample into the preset semantic extraction model to be trained to obtain a first embedded representation corresponding to the standard sample, a second embedded representation corresponding to the positive sample and a third embedded representation corresponding to the negative sample, and respectively calculating the distance between the first embedded representation, the second embedded representation and the third embedded representation by comparing a learning loss function; calculating according to the distance to obtain the model loss of the preset semantic extraction model to be trained, further judging whether the model loss is converged, if the model loss is converged, using the preset semantic extraction model to be trained as the preset semantic extraction model, if the model loss is converged, updating the preset semantic extraction model to be trained through a preset model updating method based on the gradient of the model loss calculation, and returning to the executing step: historical consultation data of clients in a building selling scene are obtained, and a training sample set of a preset semantic extraction model is determined according to the historical consultation data.
Optionally, after the steps of collecting the consultation information of the target client in the building and extracting the information semantic features of the consultation information by using a preset semantic extraction model, the preset semantic extraction model based on the contrast learning training and the timing increment learning optimization further includes:
acquiring updated consultation data sent by a cloud server at preset time intervals, and amplifying a training sample set corresponding to a preset semantic extraction model according to the updated consultation data to obtain an amplified sample set, wherein the updated consultation data is updated consultation information received by workers in the cloud server and real information semantic features corresponding to the updated consultation information. The preset time interval is preset frequency for incremental learning of the preset semantic extraction model, and may be 1 day, 30 days, 60 days or other arbitrary time intervals; performing iterative optimization on the preset semantic extraction model according to the amplification sample set, and returning to the execution step: and acquiring consultation information of target clients in the building selling places.
By means of iterative optimization of the preset semantic extraction model periodically, the characteristics extracted by the preset semantic extraction model have timeliness, and therefore accuracy of characteristic extraction is improved.
Step S20, matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer;
exemplarily, step S20 includes: and determining a target consultation intention corresponding to the consultation information according to the information semantic features, and matching the target consultation intention with a preset consultation library to obtain a matching result.
Optionally, in step S20, before the step of matching the target consulting intention corresponding to the information semantic features with a preset consulting library to obtain a matching result, the step of matching the preset consulting library with a corresponding relationship between a consulting intention and a consulting answer further includes:
obtaining common consultation intentions corresponding to each sales scene in a sales building and consultation answers corresponding to each common consultation intention, and storing each common consultation intention and the consultation answers corresponding to each common consultation intention in a correlation mode to generate the preset consultation library.
In step S20, the step of matching the target consultation intention corresponding to the information semantic feature with a preset consultation library to obtain a matching result includes:
s21, classifying the information semantic features according to the information semantic features and a preset classification model to obtain a target consultation intention corresponding to the consultation information;
and S22, inquiring the preset consulting library to obtain the matching result according to the target consulting intention.
Exemplarily, the steps S21 to S22 include: mapping the information semantic features into output vectors of preset first dimensions through a preset classification model, and classifying the information semantic features according to the output vectors to obtain target consultation intentions corresponding to the consultation information, wherein the preset first dimensions are the output dimensions of the preset classification model, and the preset dimensions are determined by the number of problems of the consultation intentions in the preset consultation library; and inquiring the preset consulting library according to the target consulting intention to obtain the matching result.
In step S21, the step of classifying the information semantic features according to the information semantic features and a preset classification model to obtain a target consultation intention corresponding to the consultation information includes:
step A10, determining the probability that the consultation information belongs to each consultation intention according to the information semantic features and a preset classification model;
step A20, judging whether a target probability in each probability is greater than a preset probability threshold value;
step A30, if the target probability exists, the consulting intention corresponding to the target probability is used as the target consulting intention;
and A40, if the inquiry information does not exist, judging that the inquiry information is the problematic information, outputting the information which cannot be answered, and sending the problematic information to a cloud server.
In this embodiment, it should be noted that the preset classification model may be a logistic regression classification model, a decision tree classification model, or a fully-connected neural network, and because the calculation amount of classification is large and the input and output feature dimensions are inconsistent, the fully-connected neural network is preferred, the preset probability threshold is a preset probability threshold for determining that the consultation information belongs to the consultation purpose, and the preset probability threshold may be 60%, 70%, or 80, or any other probability greater than 60%.
Exemplarily, the steps a10 to a40 include: mapping the information semantic features into output vectors of preset first dimensions through a preset classification model, wherein the output vectors comprise the probability that the consultation information belongs to each consultation intention; judging whether a target probability in each probability is greater than a preset probability threshold value or not; if the target probability in each probability is greater than a preset probability threshold, taking the consultation intention corresponding to the target probability as the target consultation intention; if the target probability does not exist in the probabilities and is larger than a preset probability threshold value, the consultation information is judged to be difficult information, information which cannot be answered is output, and the difficult information is sent to a cloud server.
As an example, referring to fig. 2, fig. 2 includes: advisory information (illustrated question text), information semantic features (illustrated embedded spatial vectors), a preset semantic extraction model (illustrated BERT), a preset classification model (illustrated fully connected classifier), and advisory intents (illustrated intents a, B, and C). Extracting information semantic features of the consultation information through a preset semantic extraction model, and mapping the information semantic features into the probability that the consultation information belongs to each consultation intention through a full-connection classifier.
And S30, replying the consultation information according to the matching result.
Exemplarily, step S30 includes: and outputting the matching result through a voice broadcasting system and/or a display screen to reply the consultation information.
Compared with a method for solving a problem of a client at a building through a public consultant, the embodiment of the application collects consultation information of a target client at the building and extracts information semantic features of the consultation information through a preset semantic extraction model, wherein the preset semantic extraction model is obtained based on contrast learning training and timing increment learning optimization; matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer; according to the matching result, the consultation information is responded, the response result is matched according to the information semantic features of the extracted consultation information and the information semantic features, so that the automation of the customer at the building place for reception is realized, the technical defect that all the customers cannot be received due to less business consultants at the peak of the customer flow when the customer problem is solved at the building place by the business consultants is avoided, and the customer reception efficiency at the building place is improved.
Example two
Further, referring to fig. 3, based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents to the first embodiment described above may be referred to the above description, and are not repeated again in the following. On this basis, in step S10, the preset semantic extraction model includes a word segmentation model and an information prediction model, and the step of extracting the information semantic features of the advisory information through the preset semantic extraction model includes:
step B10, extracting the information key words of the consultation information through the word segmentation model;
step B20, according to the information prediction model, predicting to obtain mask information corresponding to the information key words;
and B30, integrating the information key words and the mask information to obtain the information semantic features of the consultation information.
In this embodiment, it should be noted that the preset semantic extraction model may be a feature extraction model, and may also be a BERT (bidirectional encoder representation based on a Transformer) model.
Exemplarily, the steps B10 to B30 include: screening and extracting the synonymous words according to the part of speech and the meaning of each word in the consultation information through the word segmentation model to obtain information key words of the consultation information; mapping the key word characteristics corresponding to the information key words into mask information corresponding to the information key words through the information prediction model; and integrating the information key words and the mask information to obtain the information semantic features of the consultation information, wherein the feature dimension of the information semantic features is a preset second dimension, the preset second dimension is the dimension of the information semantic features obtained by extracting the features of the consultation information, and the mask information is predicted through an information prediction model to expand the semantic features of the consultation information, so that more decision bases are provided for information semantic feature classification, and the classification accuracy of the consultation information classification is improved.
It is understood that the BERT model includes a plurality of types, for example, a conventional BERT model, a BERT-wwm-ext model, and a BERT-wwm model, and since the related content of the building sales scenes at the building sales frequently appears in the news information, the prediction results of the BERT-wwm-ext model for the news information scenes are more accurate according to the training results of the models for different scenes, so that the BERT-wwm-ext model is preferable.
In step S21, before the step of classifying the information semantic features according to the information semantic features and a preset classification model to obtain a target consulting intention corresponding to the consulting information, the method further includes:
step C10, acquiring a preset classification model to be trained, a training sample and a real consultation intention corresponding to the training sample, wherein the model structure of the preset classification model to be trained is determined by the number of questions of the consultation intention in the preset consultation library;
step C20, obtaining the training probability of the training sample belonging to each consultation intention according to the preset classification model to be trained and the training sample;
and step C30, performing iterative optimization on the preset classification model to be trained according to each training probability and the real consultation intention to obtain the preset classification model.
Exemplarily, the steps C10 to C30 include: determining a model structure of the to-be-trained preset classification model according to the number of the problems of the consultation intentions in the preset consultation library, performing normal distribution assignment on the model weight of the to-be-trained classification model, and constructing the to-be-trained preset classification model according to the model structure and the model weight; taking the consultation information of a historical client as a training sample of the preset classification model to be trained, and obtaining the real consultation intention of the training sample; mapping semantic features corresponding to the training samples into training probabilities of the training samples with preset first dimensionality belonging to the consultation intents through the to-be-trained preset classification model, calculating model losses of the to-be-trained preset classification model according to the training probabilities, the real consultation intents and a cross entropy calculation formula, further judging whether the model losses are converged, if the model losses are converged, using the to-be-trained preset classification model as the preset classification model, if the model losses are not converged, updating the to-be-trained preset classification model through a preset model updating method based on the gradient calculated by the model losses, and returning to the execution step: the method comprises the steps of obtaining a preset classification model to be trained, a training sample and a real consultation intention corresponding to the training sample, wherein the updating method of the preset model comprises a gradient descent method, a gradient ascent method and the like.
In step a40, after the step of determining that the advisory information is problematic information, outputting unanswerable information, and sending the problematic information to a cloud server, the method further includes:
step A50, acquiring a problem consultation intention corresponding to the problem information sent by the cloud server and a corresponding problem consultation answer, wherein the problem consultation intention and the problem consultation answer are determined by a worker according to the problem information;
step A60, updating the preset consulting library according to the difficult consulting intention and the difficult consulting answer to obtain an updated question-answer library;
step A70, according to the problem information and the updated question-answer library, amplifying training samples of a preset classification model, and returning to the execution step: and obtaining the training probability of the training sample belonging to each consultation intention according to a preset classification model to be trained and the training sample.
Exemplarily, the steps a50 to a70 include: when a cloud server detects that trouble information is received, outputting the trouble information for a worker to check the trouble information, wherein the step of outputting the trouble information can be sending the trouble information to a mobile terminal of the worker, and/or outputting the trouble information through a server screen of the cloud server and/or a server broadcasting system, when the cloud server receives a trouble consultation intention corresponding to the trouble information operated by the mobile terminal and/or the worker in the cloud server and a corresponding trouble consultation answer, sending the trouble consultation intention and the trouble consultation answer to a receiving system at a sales premises, and obtaining the trouble consultation intention corresponding to the trouble information sent by the cloud server and the corresponding trouble consultation answer through the receiving system at the sales premises; the questioning and questioning consultation intention and the questioning and questioning answer are stored in the preset consulting library in a correlation mode so as to update the preset consulting library to obtain an updated questioning and answering library; adjusting the model structure of the preset classification model to be trained according to the updated question-answer library, amplifying the training samples according to the difficult consultation information, the difficult consultation intention corresponding to the difficult consultation information and the corresponding difficult consultation answer, and returning to the execution step: and obtaining the training probability of the training sample belonging to each consultation intention according to a preset classification model to be trained and the training sample.
Compared with a method for solving a problem of a client at a building through a public consultant, the embodiment of the application collects consultation information of a target client at the building and extracts information semantic features of the consultation information through a preset semantic extraction model, wherein the preset semantic extraction model is obtained based on contrast learning training and timing increment learning optimization; matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer; according to the matching result, the consultation information is responded, the response result is matched according to the information semantic features of the extracted consultation information and the information semantic features, so that the automation of the customer at the building place for reception is realized, the technical defect that all the customers cannot be received due to less business consultants at the peak of the customer flow when the customer problem is solved at the building place by the business consultants is avoided, and the customer reception efficiency at the building place is improved.
EXAMPLE III
The embodiment of the present application further provides a reception device at a building, where the reception device is applied to a reception device at a building, and referring to fig. 4, the reception device at a building includes:
the system comprises an extraction module, a comparison learning module and a timing increment learning optimization module, wherein the extraction module is used for acquiring consultation information of a target client in a building and extracting information semantic features of the consultation information through a preset semantic extraction model, and the preset semantic extraction model is obtained based on comparison learning training and timing increment learning optimization;
the matching module is used for matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer;
and the reply module is used for replying the consultation information according to the matching result.
Optionally, before the information semantic features of the advisory information are extracted through a preset semantic extraction model, where the preset semantic extraction model is obtained based on a contrast learning training and a timing increment learning optimization, the reception device at the building sales location is further configured to:
obtaining historical consultation data of clients in a building selling scene, and determining a training sample set of a preset semantic extraction model according to the historical consultation data;
constructing an enhanced sample set of the training sample set, wherein the enhanced sample set comprises a standard sample, a positive sample and a negative sample, the standard sample is standard consulting information corresponding to each consulting intention, the positive sample is related consulting information corresponding to each consulting sentence pattern with similar semantics with the consulting intention, and the negative sample is unrelated consulting information corresponding to each consulting sentence pattern without similar semantics with the consulting intention;
and performing iterative optimization on the preset semantic extraction model to be trained according to the enhanced sample set to obtain the preset semantic extraction model.
Optionally, before the step of extracting the information semantic features of the advisory information through the preset semantic extraction model, the reception apparatus at the building is further configured to:
acquiring the length of information bytes of the consultation information;
judging whether the length of the information byte is larger than a preset byte threshold value or not;
if yes, executing the following steps: extracting information semantic features of the consultation information through a preset semantic extraction model;
if not, extracting the information semantic features of the consultation information through singular value decomposition, and executing the following steps: and matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result.
Optionally, the preset semantic extraction model includes a word segmentation model and an information prediction model, and the extraction module is further configured to:
extracting information key words of the consultation information through the word segmentation model;
according to the information prediction model, mask information corresponding to the information key words is obtained through prediction;
and integrating the information key words and the mask information to obtain the information semantic features of the consultation information.
Optionally, the matching module is further configured to:
classifying the information semantic features according to the information semantic features and a preset classification model to obtain a target consultation intention corresponding to the consultation information;
and inquiring the preset consultation library according to the target consultation intention to obtain the matching result.
Optionally, the matching module is further configured to:
determining the probability of the consultation information belonging to each consultation intention according to the information semantic features and a preset classification model;
judging whether the target probability in each probability is greater than a preset probability threshold value or not;
if so, taking the consultation intention corresponding to the target probability as the target consultation intention;
if not, judging that the consultation information is difficult information, outputting information which cannot be answered, and sending the difficult information to a cloud server.
Optionally, before the step of classifying the information semantic features according to the information semantic features and a preset classification model to obtain a target consultation intention corresponding to the consultation information, the reception device at the building sales location is further configured to:
acquiring a preset classification model to be trained, a training sample and a real consultation intention corresponding to the training sample, wherein the model structure of the preset classification model to be trained is determined by the number of questions of the consultation intention in the preset consultation library;
obtaining the training probability of the training sample belonging to each consultation intention according to the preset classification model to be trained and the training sample;
and performing iterative optimization on the preset classification model to be trained according to each training probability and the real consultation intention to obtain the preset classification model.
Optionally, after the step of determining that the consultation information is problematic information, outputting unanswered information, and sending the problematic information to a cloud server, the reception apparatus at the building is further configured to:
acquiring a difficult consultation intention corresponding to the difficult information sent by the cloud server and a corresponding difficult consultation answer, wherein the difficult consultation intention and the difficult consultation answer are determined by a worker according to the difficult information;
updating the preset consultation library according to the difficult consultation intention and the difficult consultation response to obtain an updated question-answer library;
according to the problem information and the updated question-answer library, amplifying training samples of a preset classification model, and returning to the execution step: and obtaining the training probability of the training sample belonging to each consultation intention according to a preset classification model to be trained and the training sample.
The reception device at the building sales department provided by the application adopts the reception method at the building sales department in the embodiment, so that the technical problem of low customer reception efficiency at the building sales department is solved. Compared with the prior art, the beneficial effects of the reception device at the building place provided by the embodiment of the application are the same as the beneficial effects of the reception method at the building place provided by the embodiment, and other technical features of the reception device at the building place are the same as those disclosed by the method of the embodiment, which are not repeated herein.
Example four
An embodiment of the present application provides an electronic device, which includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method for hospitality at a retail location of the above-described embodiments.
Referring now to FIG. 5, shown is a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, the electronic device may include a processing means (e.g., a central processing unit, a graphic processor, etc.) that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage means into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the electronic apparatus are also stored. The processing device, the ROM, and the RAM are connected to each other by a bus. An input/output (I/O) interface is also connected to the bus.
Generally, the following systems may be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, and the like; output devices including, for example, liquid Crystal Displays (LCDs), speakers, vibrators, and the like; storage devices including, for example, magnetic tape, hard disk, and the like; and a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While the figures illustrate an electronic device with various systems, it is to be understood that not all illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, the processes described above with reference to the flow diagrams may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from a storage means, or installed from a ROM. The computer program, when executed by a processing device, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
The electronic equipment provided by the application adopts the reception method at the building sales department in the embodiment, so that the technical problem of low customer reception efficiency at the building sales department is solved. Compared with the prior art, the beneficial effects of the electronic device provided by the embodiment of the application are the same as the beneficial effects of the method for reception at a building provided by the embodiment, and other technical features of the electronic device are the same as those disclosed by the method of the embodiment, which are not repeated herein.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
EXAMPLE five
The present embodiments provide a computer readable storage medium having computer readable program instructions stored thereon for performing the method of the hospitality method at a retail establishment of the above embodiments.
The computer readable storage medium provided by the embodiments of the present application may be, for example, a usb disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the above. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer-readable storage medium may be embodied in an electronic device; or may be separate and not incorporated into the electronic device.
The computer readable storage medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring consultation information of a target client in a building, and extracting information semantic features of the consultation information through a preset semantic extraction model, wherein the preset semantic extraction model is obtained based on contrast learning training and timing increment learning optimization; matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer; and replying the consultation information according to the matching result.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the names of the modules do not in some cases constitute a limitation of the unit itself.
The computer-readable storage medium provided by the application stores computer-readable program instructions for executing the reception method at the building, and solves the technical problem of low customer reception efficiency at the building. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the embodiment of the application are the same as the beneficial effects of the reception method for the building sales department provided by the implementation, and are not repeated herein.
EXAMPLE six
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the hospitality method at a sales premises as described above.
The computer program product provided by the application solves the technical problem of low customer reception efficiency at a building selling place. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as the beneficial effects of the reception method at the building sales location provided by the above embodiment, and are not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. A reception method at a building, the reception method at the building comprising:
acquiring consultation information of a target client in a building, and extracting information semantic features of the consultation information through a preset semantic extraction model, wherein the preset semantic extraction model is obtained based on contrast learning training and timing increment learning optimization;
matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result, wherein the preset consultation library comprises a corresponding relation between the consultation intention and a consultation answer;
and replying the consultation information according to the matching result.
2. The method for building reception according to claim 1, wherein before the step of extracting the information semantic features of the consulting information by using a preset semantic extraction model, the preset semantic extraction model is based on a contrast learning training and a timing increment learning optimization, the method further comprises:
acquiring historical consultation data of a client in a building selling scene, and determining a training sample set of a preset semantic extraction model according to the historical consultation data;
constructing an enhanced sample set of the training sample set, wherein the enhanced sample set comprises a standard sample, a positive sample and a negative sample, the standard sample is standard consulting information corresponding to each consulting intention, the positive sample is related consulting information corresponding to each consulting sentence pattern with similar semantics with the consulting intention, and the negative sample is unrelated consulting information corresponding to each consulting sentence pattern without similar semantics with the consulting intention;
and performing iterative optimization on the preset semantic extraction model to be trained according to the enhanced sample set to obtain the preset semantic extraction model.
3. The hospitality method at the building sale location of claim 1, wherein said preset semantic extraction model comprises a word segmentation model and an information prediction model, and said step of extracting information semantic features of said counseling information through said preset semantic extraction model comprises:
extracting information key words of the consultation information through the word segmentation model;
according to the information prediction model, mask information corresponding to the information key words is obtained through prediction;
and integrating the information key words and the mask information to obtain the information semantic features of the consultation information.
4. The reception method for the building sales department according to claim 1, wherein the step of matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result comprises:
classifying the information semantic features according to the information semantic features and a preset classification model to obtain a target consultation intention corresponding to the consultation information;
and inquiring the preset consultation library according to the target consultation intention to obtain the matching result.
5. The reception method of claim 4, wherein the step of classifying the information semantic features according to the information semantic features and a preset classification model to obtain a target consultation intention corresponding to the consultation information comprises:
determining the probability that the consultation information belongs to each consultation intention according to the information semantic features and a preset classification model;
judging whether the target probability in each probability is greater than a preset probability threshold value or not;
if so, taking the consultation intention corresponding to the target probability as the target consultation intention;
if the inquiry information does not exist, judging that the consultation information is difficult information, outputting information which cannot be answered, and sending the difficult information to a cloud server.
6. The method as claimed in claim 4, wherein before the step of classifying the information semantic features according to the information semantic features and a preset classification model to obtain the target consultation purpose corresponding to the consultation information, the method further comprises:
acquiring a preset classification model to be trained, a training sample and a real consultation intention corresponding to the training sample, wherein the model structure of the preset classification model to be trained is determined by the number of questions of the consultation intention in the preset consultation library;
obtaining the training probability of the training sample belonging to each consultation intention according to the preset classification model to be trained and the training sample;
and performing iterative optimization on the preset classification model to be trained according to each training probability and the real consultation intention to obtain the preset classification model.
7. The method of claim 5, wherein after the steps of determining that the consultation information is problematic information, outputting unanswered information, and sending the problematic information to a cloud server, the method further comprises:
acquiring a difficult consultation intention corresponding to the difficult information sent by the cloud server and a corresponding difficult consultation answer, wherein the difficult consultation intention and the difficult consultation answer are determined by a worker according to the difficult information;
updating the preset consulting library according to the difficult consulting intention and the difficult consulting answer to obtain an updated questioning and answering library;
according to the problem information and the updated question-answer library, amplifying training samples of a preset classification model, and returning to the execution step: and obtaining the training probability of the training sample belonging to each consultation intention according to a preset classification model to be trained and the training sample.
8. The method for building reception according to claim 1, wherein before the step of extracting the information semantic features of the consulting information by using the preset semantic extraction model, the method further comprises:
acquiring the information byte length of the consultation information;
judging whether the length of the information byte is larger than a preset byte threshold value or not;
if yes, executing the following steps: extracting information semantic features of the consultation information through a preset semantic extraction model;
if not, extracting the information semantic features of the consultation information through singular value decomposition, and executing the following steps: and matching the target consultation intention corresponding to the information semantic features with a preset consultation library to obtain a matching result.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and (c) a second step of,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the hospitality method at the premises of any of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program for implementing a method of hospitality at a sales premises, the program being executed by a processor for implementing the steps of the method of hospitality at a sales premises according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211081898.0A CN115170210A (en) | 2022-09-06 | 2022-09-06 | Reception method at building, electronic device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211081898.0A CN115170210A (en) | 2022-09-06 | 2022-09-06 | Reception method at building, electronic device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115170210A true CN115170210A (en) | 2022-10-11 |
Family
ID=83481541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211081898.0A Pending CN115170210A (en) | 2022-09-06 | 2022-09-06 | Reception method at building, electronic device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115170210A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104142918A (en) * | 2014-07-31 | 2014-11-12 | 天津大学 | Short text clustering and hotspot theme extraction method based on TF-IDF characteristics |
| CN111414457A (en) * | 2020-03-20 | 2020-07-14 | 深圳前海微众银行股份有限公司 | Intelligent question-answering method, device, equipment and storage medium based on federal learning |
| CN111667817A (en) * | 2020-06-22 | 2020-09-15 | 平安资产管理有限责任公司 | Voice recognition method, device, computer system and readable storage medium |
| CN112446405A (en) * | 2019-09-04 | 2021-03-05 | 杭州九阳小家电有限公司 | User intention guiding method for home appliance customer service and intelligent home appliance |
| CN112836025A (en) * | 2019-11-22 | 2021-05-25 | 航天信息股份有限公司 | Intention identification method and device |
| CN113836274A (en) * | 2021-11-25 | 2021-12-24 | 平安科技（深圳）有限公司 | Abstract extraction method, device, equipment and medium based on semantic analysis |
| CN114398910A (en) * | 2022-01-19 | 2022-04-26 | 平安科技（深圳）有限公司 | Intelligent question and answer method, device, equipment and storage medium |
| CN114580407A (en) * | 2022-03-03 | 2022-06-03 | 武汉东湖大数据交易中心股份有限公司 | Intelligent consulting method and system for industry recruitment in park based on maximum entropy |
| CN114781651A (en) * | 2022-05-23 | 2022-07-22 | 清华大学深圳国际研究生院 | Small sample learning robustness improving method based on contrast learning |
-
2022
- 2022-09-06 CN CN202211081898.0A patent/CN115170210A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104142918A (en) * | 2014-07-31 | 2014-11-12 | 天津大学 | Short text clustering and hotspot theme extraction method based on TF-IDF characteristics |
| CN112446405A (en) * | 2019-09-04 | 2021-03-05 | 杭州九阳小家电有限公司 | User intention guiding method for home appliance customer service and intelligent home appliance |
| CN112836025A (en) * | 2019-11-22 | 2021-05-25 | 航天信息股份有限公司 | Intention identification method and device |
| CN111414457A (en) * | 2020-03-20 | 2020-07-14 | 深圳前海微众银行股份有限公司 | Intelligent question-answering method, device, equipment and storage medium based on federal learning |
| CN111667817A (en) * | 2020-06-22 | 2020-09-15 | 平安资产管理有限责任公司 | Voice recognition method, device, computer system and readable storage medium |
| CN113836274A (en) * | 2021-11-25 | 2021-12-24 | 平安科技（深圳）有限公司 | Abstract extraction method, device, equipment and medium based on semantic analysis |
| CN114398910A (en) * | 2022-01-19 | 2022-04-26 | 平安科技（深圳）有限公司 | Intelligent question and answer method, device, equipment and storage medium |
| CN114580407A (en) * | 2022-03-03 | 2022-06-03 | 武汉东湖大数据交易中心股份有限公司 | Intelligent consulting method and system for industry recruitment in park based on maximum entropy |
| CN114781651A (en) * | 2022-05-23 | 2022-07-22 | 清华大学深圳国际研究生院 | Small sample learning robustness improving method based on contrast learning |
Non-Patent Citations (1)
| Title |
|---|
| 汪晨曦: "基于BERT的法律问答***", 《中国优秀硕士学位论文全文数据库 (社会科学Ⅰ辑)》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110019616B (en) | POI (Point of interest) situation acquisition method and equipment, storage medium and server thereof | |
| CN111381909A (en) | Page display method and device, terminal equipment and storage medium | |
| US20240127795A1 (en) | Model training method, speech recognition method, device, medium, and apparatus | |
| US20190147539A1 (en) | Method and apparatus for outputting information | |
| CN113765928B (en) | Internet of things intrusion detection method, equipment and medium | |
| CN111291071A (en) | Data processing method and device and electronic equipment | |
| US11842163B2 (en) | Method and apparatus for generating prediction information, and electronic device and medium | |
| CN111738316B (en) | Zero sample learning image classification method and device and electronic equipment | |
| WO2022188534A1 (en) | Information pushing method and apparatus | |
| CN115062617A (en) | Task processing method, device, equipment and medium based on prompt learning | |
| US20230041339A1 (en) | Method, device, and computer program product for user behavior prediction | |
| CN116028868B (en) | Equipment fault classification method and device, electronic equipment and readable storage medium | |
| CN111488386B (en) | Data query method and device | |
| US20220327147A1 (en) | Method for updating information of point of interest, electronic device and storage medium | |
| CN115170210A (en) | Reception method at building, electronic device and readable storage medium | |
| CN110659208A (en) | Test data set updating method and device | |
| Peng | Statistical analysis of employee retention | |
| CN110458743B (en) | Community management method, device, equipment and storage medium based on big data analysis | |
| WO2021151354A1 (en) | Word recognition method and apparatus, computer device, and storage medium | |
| CN111339770A (en) | Method and apparatus for outputting information | |
| CN115470292B (en) | Block chain consensus method, device, electronic equipment and readable storage medium | |
| CN110795424A (en) | Feature engineering variable data request processing method and device and electronic equipment | |
| CN115168478B (en) | Data type conversion method, electronic device and readable storage medium | |
| CN113177174B (en) | Feature construction method, content display method and related device | |
| CN116757461B (en) | Method, device, equipment and medium for displaying updated power grid infrastructure service node information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221011 |
|
| RJ01 | Rejection of invention patent application after publication |