CN118093626A - Information processing method and device, computer storage medium and electronic equipment - Google Patents
Information processing method and device, computer storage medium and electronic equipment Download PDFInfo
- Publication number
- CN118093626A CN118093626A CN202410237692.5A CN202410237692A CN118093626A CN 118093626 A CN118093626 A CN 118093626A CN 202410237692 A CN202410237692 A CN 202410237692A CN 118093626 A CN118093626 A CN 118093626A
- Authority
- CN
- China
- Prior art keywords
- information
- consultation
- target
- similarity
- maintenance personnel
- 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
- 230000010365 information processing Effects 0.000 title claims abstract description 32
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000003672 processing method Methods 0.000 title abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 121
- 238000012423 maintenance Methods 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000013135 deep learning Methods 0.000 claims description 59
- 238000012549 training Methods 0.000 claims description 19
- 238000012216 screening Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000004806 packaging method and process Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000009223 counseling Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an information processing method, an information processing device, a computer storage medium and electronic equipment. To the field of artificial intelligence or other related fields, the method comprising: receiving a target consultation request sent by a user through a client, and identifying the target consultation request to obtain target consultation information; candidate consultation information associated with the target consultation information is obtained from the historical database, similarity data of the candidate consultation information and the target consultation information are calculated, a processing result associated with the matched consultation information is obtained under the condition that the information similarity is larger than a similarity threshold value, and the processing result is sent to the client; and under the condition that the information similarity is smaller than or equal to a similarity threshold, identifying target consultation information to obtain a first information keyword, and sending a target consultation request to a target client used by operation and maintenance personnel. The application solves the problem of low accuracy of the provided processing result when the processing result of the target consultation request is provided for the user in the related technology.
Description
Technical Field
The present application relates to the field of artificial intelligence or other related fields, and in particular, to a method and apparatus for processing information, a computer storage medium, and an electronic device.
Background
When collecting and summarizing opinions in a financial institution, statistics personnel often need to spend a great deal of time and effort to manually collect various opinions or suggestions and to perform summary finishing, but the method is easy to repeatedly work, and affects the working efficiency and accuracy. Meanwhile, the manual operation also easily causes errors and omission of data, accuracy and reliability of statistical results are further affected, and in addition, a large amount of human resource investment is needed for the manual operation, so that cost and burden are increased.
In addition, the collecting and summarizing method of opinion suggestions in the traditional mode also has the problems of incomplete information collection, difficulty in timely updating, difficulty in data analysis and mining and the like, so that real and comprehensive opinions and suggestions are difficult to obtain timely, and the scientificity and effectiveness of decisions are affected.
Aiming at the problem of low accuracy of the provided processing result when the processing result of the target consultation request is provided for the user in the related technology, no effective solution is proposed at present.
Disclosure of Invention
The application mainly aims to provide an information processing method, an information processing device, a computer storage medium and electronic equipment, so as to solve the problem that the accuracy of the provided processing result is low when the processing result of a target consultation request is provided for a user in the related technology.
In order to achieve the above object, according to one aspect of the present application, there is provided an information processing method. The method comprises the following steps: receiving a target consultation request sent by a user through a client, and identifying the target consultation request to obtain target consultation information; candidate consultation information associated with the target consultation information is obtained from the historical database, similarity data of the candidate consultation information and the target consultation information is calculated, and information similarity is obtained; under the condition that the information similarity is larger than a similarity threshold, determining candidate consultation information as matched consultation information, acquiring a processing result associated with the matched consultation information, and sending the processing result to the client; and under the condition that the information similarity is smaller than or equal to a similarity threshold, identifying target consultation information to obtain a first information keyword, and sending a target consultation request to a target client used by operation and maintenance personnel according to the first information keyword, wherein the first information keyword is used for screening the operation and maintenance personnel.
Further, obtaining candidate advisory information associated with the target advisory information from the historical database includes: preprocessing target consultation information to obtain initial processing information, wherein the preprocessing mode at least comprises one of the following steps: data cleaning and format conversion; extracting information keywords from the initial processing information to obtain a group of second information keywords, wherein the group of second information keywords refer to words representing the counseling contents in the target counseling request; acquiring N pieces of historical consultation information stored in a historical database, and extracting keywords of the N pieces of historical consultation information to obtain N groups of third information keywords, wherein N is a positive integer; and calculating the similarity of a group of second information keywords and each group of third information keywords to obtain N pieces of keyword similarity data, obtaining historical consultation information associated with the keyword similarity data with the largest numerical value, and determining the historical consultation information as candidate consultation information.
Further, identifying the target consultation information to obtain the first information keyword includes: performing word segmentation processing on target consultation information to obtain M consultation words, and performing format conversion processing on the M consultation words to obtain M converted consultation words, wherein M is a positive integer; acquiring a preset vocabulary list, inputting the preset vocabulary list and M converted consultation words into a deep learning network model to obtain a recognition result, wherein the deep learning network model is used for carrying out text recognition processing on the M converted consultation words, and the preset vocabulary list comprises a plurality of preset types of vocabularies; under the condition that the recognition result represents that the M converted consultation words do not contain various vocabularies of preset types, determining target consultation information as safety information, and screening information keywords from the M converted consultation words to obtain first information keywords; and stopping executing the step of sending the target consultation request to the target client used by the operation and maintenance personnel according to the first information keyword under the condition that the recognition result represents that the M converted consultation words contain a plurality of preset types.
Further, the deep learning network model is obtained through training of the following steps: acquiring a preset deep learning network model, acquiring Y pieces of historical consultation information and historical recognition results related to the Y pieces of historical consultation information from a historical database, and combining the Y pieces of historical consultation information and the Y pieces of historical recognition results to obtain a training information set, wherein Y is a positive integer; training a preset deep learning network model by using a training information set to obtain a trained deep learning network model; acquiring the recognition accuracy associated with the trained deep learning network model, and under the condition that the recognition accuracy is smaller than or equal to the preset accuracy, performing parameter adjustment on the trained deep learning network model by utilizing an optimization algorithm until the recognition accuracy of the adjusted deep learning network model is larger than the preset accuracy, and determining the adjusted deep learning network model as the deep learning network model.
Further, sending the target consultation request to the target client used by the operation and maintenance personnel according to the first information keyword comprises: acquiring a candidate operation and maintenance personnel list, and screening information of target operation and maintenance personnel from the candidate operation and maintenance personnel list according to a first information keyword, wherein the candidate operation and maintenance personnel list comprises information of Z operation and maintenance personnel, and Z is a positive integer; and determining a target client according to the information of the target operation and maintenance personnel, and sending a target consultation request to the target client.
Further, after the target consultation request is sent to the target client used by the operation and maintenance personnel according to the first information keyword, the method further comprises: receiving a processing result fed back by operation and maintenance personnel through a target client; and packaging the processing result, the target consultation information and the user information of the user, and storing the packaged information into a history database.
Further, a plurality of history consultation information is stored in the history database, wherein each history consultation information is associated with a processing result, user information of a user who sends each history consultation information, and an information tag, the information tag is used for representing a consultation type of the plurality of history consultation information, the information tag of the plurality of history consultation information is obtained before the N pieces of history consultation information stored in the history database are obtained, and the step of obtaining the N pieces of history consultation information stored in the history database is performed according to the information tag of the plurality of history consultation information.
In order to achieve the above object, according to another aspect of the present application, there is provided an information processing apparatus. The device comprises: the first receiving unit is used for receiving a target consultation request sent by a user through a client, identifying the target consultation request and obtaining target consultation information; the acquisition unit is used for acquiring candidate consultation information associated with the target consultation information from the historical database, calculating similarity data of the candidate consultation information and the target consultation information, and obtaining information similarity; the determining unit is used for determining the candidate consultation information as the matched consultation information under the condition that the information similarity is larger than a similarity threshold value, acquiring a processing result associated with the matched consultation information and sending the processing result to the client; the identifying unit is used for identifying the target consultation information to obtain a first information keyword under the condition that the information similarity is smaller than or equal to a similarity threshold value, and sending a target consultation request to a target client used by operation and maintenance personnel according to the first information keyword, wherein the first information keyword is used for screening the operation and maintenance personnel.
According to another aspect of the embodiment of the present invention, there is also provided a computer storage medium for storing a program, where the program controls a device in which the computer storage medium is located to execute an information processing method when running.
According to another aspect of embodiments of the present invention, there is also provided an electronic device including one or more processors and a memory; the memory has stored therein computer readable instructions for execution by the processor, wherein the computer readable instructions when executed perform a method of processing information.
According to another aspect of the embodiments of the present invention, there is also provided a computer program product comprising a computer program which, when executed by a processor, performs a method of processing information.
According to the application, the following steps are adopted: receiving a target consultation request sent by a user through a client, and identifying the target consultation request to obtain target consultation information; candidate consultation information associated with the target consultation information is obtained from the historical database, similarity data of the candidate consultation information and the target consultation information is calculated, and information similarity is obtained; under the condition that the information similarity is larger than a similarity threshold, determining candidate consultation information as matched consultation information, acquiring a processing result associated with the matched consultation information, and sending the processing result to the client; under the condition that the information similarity is smaller than or equal to a similarity threshold, identifying target consultation information to obtain a first information keyword, sending a target consultation request to a target client used by operation and maintenance personnel according to the first information keyword, wherein the first information keyword is used for screening the operation and maintenance personnel, solving the problem that the accuracy of the provided processing result is low when the processing result of the target consultation request is provided for a user in the related technology, obtaining the target consultation information by identifying the target consultation request sent by the user through the client, calculating the similarity data of candidate consultation information and the target consultation information obtained from a historical database to obtain the information similarity, under the condition that the information similarity is larger than the similarity threshold, sending the processing result associated with the candidate consultation information to the client, under the condition that the information similarity is smaller than or equal to the similarity threshold, identifying the target consultation information to obtain the first information keyword, and sending the target consultation request to the target client used by the operation and maintenance personnel, and further achieving the effect of improving the accuracy of the provided processing result.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a flow chart of a method of processing information provided in accordance with an embodiment of the present application;
FIG. 2 is a schematic diagram of a method for determining candidate advisory information provided in accordance with an embodiment of the present application;
FIG. 3 is a schematic diagram of an information processing apparatus provided according to an embodiment of the present application;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.
The present application will be described with reference to preferred implementation steps, and fig. 1 is a flowchart of a method for processing information provided according to an embodiment of the present application, as shown in fig. 1, and the method includes the following steps:
step S101, receiving a target consultation request sent by a user through a client, and identifying the target consultation request to obtain target consultation information.
Specifically, the target consultation request includes suggestions and comments made by the user for related business or service of the financial institution, the client may be associated with a mobile device used by the user or related devices of the website of the financial institution, when the user wants to make some suggestions or want to inquire related information to the institution after handling the financial business in the financial institution, the user may initiate a target consultation request through the client, and after receiving the target consultation request, an information collecting system associated with the financial institution may identify the target consultation request, so as to obtain target consultation information, for example, how the target consultation information may be registered in an account, where when identifying the target consultation request, the target consultation request may be identified by using a fuzzy identification technology.
Step S102, candidate consultation information associated with the target consultation information is obtained from the historical database, similarity data of the candidate consultation information and the target consultation information is calculated, and information similarity is obtained.
Specifically, the historical database may be a database associated with a financial institution and used for storing information data, the candidate advisory information may be advisory information associated with advisory requests sent by other users in a historical time period, and after the information collection system associated with the financial institution identifies the target advisory information, the associated advisory information may be screened out from the historical database according to the target advisory information and used as the candidate advisory information. Further, the candidate consultation information and the target consultation information are subjected to similarity calculation, so that the information similarity is obtained, and whether the associated processing result of the candidate consultation information can be used as the processing result of the target consultation request can be judged by utilizing the information similarity.
Step S103, under the condition that the information similarity is larger than a similarity threshold, the candidate consultation information is determined to be the matched consultation information, a processing result associated with the matched consultation information is obtained, and the processing result is sent to the client.
Specifically, when the information similarity of the candidate advisory information and the target advisory information is greater than the set similarity threshold, it is indicated that the target advisory information and the candidate advisory information are higher in similarity, at this time, the processing result associated with the candidate advisory information stored in the history database may be directly obtained, and the processing result is sent to the request issuer as the processing result of the target advisory request, that is, the processing result is sent to the user.
Step S104, under the condition that the information similarity is smaller than or equal to a similarity threshold, identifying target consultation information to obtain a first information keyword, and sending a target consultation request to a target client used by operation and maintenance personnel according to the first information keyword, wherein the first information keyword is used for screening the operation and maintenance personnel.
Specifically, if the information similarity between the candidate advisory information and the target advisory information is smaller than or equal to the set similarity threshold, it may indicate that the target advisory information and the candidate advisory information are lower in similarity, or it may also indicate that the target advisory request has no similar request issued by the user in the historical time period, at this time, keywords in the target advisory information may be identified, so as to obtain information keywords (i.e., first information keywords) for screening the operation and maintenance personnel, and further determine the operation and maintenance personnel by using the first information keywords, send the target advisory request to the client used by the operation and maintenance personnel, and after receiving the target advisory request, the operation and maintenance personnel perform manual processing, and return the processing result to the client used by the user.
According to the information processing method provided by the embodiment of the application, the target consultation request is identified by receiving the target consultation request sent by the user through the client, so as to obtain target consultation information; candidate consultation information associated with the target consultation information is obtained from the historical database, similarity data of the candidate consultation information and the target consultation information is calculated, and information similarity is obtained; under the condition that the information similarity is larger than a similarity threshold, determining candidate consultation information as matched consultation information, acquiring a processing result associated with the matched consultation information, and sending the processing result to the client; under the condition that the information similarity is smaller than or equal to a similarity threshold, identifying target consultation information to obtain a first information keyword, sending a target consultation request to a target client used by operation and maintenance personnel according to the first information keyword, wherein the first information keyword is used for screening the operation and maintenance personnel, solving the problem that the accuracy of the provided processing result is low when the processing result of the target consultation request is provided for a user in the related technology, obtaining the target consultation information by identifying the target consultation request sent by the user through the client, calculating the similarity data of candidate consultation information and the target consultation information obtained from a historical database to obtain the information similarity, under the condition that the information similarity is larger than the similarity threshold, sending the processing result associated with the candidate consultation information to the client, under the condition that the information similarity is smaller than or equal to the similarity threshold, identifying the target consultation information to obtain the first information keyword, and sending the target consultation request to the target client used by the operation and maintenance personnel, and further achieving the effect of improving the accuracy of the provided processing result.
Fig. 2 is a schematic diagram of a method for determining candidate advisory information provided according to an embodiment of the present application by calculating similarity with target advisory information, as shown in fig. 2, optionally, in the method for processing information provided by the embodiment of the present application, obtaining candidate advisory information associated with target advisory information from a historical database includes:
step S201, preprocessing target consultation information to obtain initial processing information, wherein the preprocessing mode at least comprises one of the following steps: data cleaning and format conversion;
step S202, extracting information keywords from the initial processing information to obtain a group of second information keywords, wherein the group of second information keywords refer to words representing the counseling contents in the target counseling request;
Step S203, N pieces of history consultation information stored in a history database are obtained, keywords of the N pieces of history consultation information are extracted, and N groups of third information keywords are obtained, wherein N is a positive integer;
Step S204, calculating the similarity between a group of second information keywords and each group of third information keywords, obtaining N pieces of keyword similarity data, obtaining historical consultation information associated with the keyword similarity data with the largest numerical value, and determining the historical consultation information as candidate consultation information.
Specifically, when the advisory information in the history period associated with the target advisory information is screened, the target advisory information may be processed first, for example, data cleaning processing may be performed on the target advisory information, for example, repeated, erroneous, incomplete or invalid information in the target advisory information is removed, and conversion processing is performed on the format of the target advisory information, so that the received target advisory information is more normalized and is convenient for subsequent processing, thereby obtaining the initial processing information. Meanwhile, information keywords (namely second information keywords) can be extracted from the initial processing information obtained through processing so as to facilitate subsequent information matching and similarity calculation, wherein the second information keywords can represent the consultation content of the target consultation request and can identify the requirements of users.
Further, according to the consultation type of the target consultation request, historical consultation information of a plurality of historical time periods is obtained from the historical database, and information keywords of the historical consultation information are extracted to obtain a plurality of groups of third information keywords. And then, calculating the similarity of a group of second information keywords associated with the target consultation request and a plurality of groups of third information keywords associated with the historical consultation information, so that corresponding keyword similarity data can be obtained, further, keyword similarity data with the largest numerical value is selected from the calculated plurality of keyword similarity data, and the historical consultation information associated with the keyword similarity data is determined to be candidate consultation information. The embodiment lays a foundation for the subsequent feedback processing result by preprocessing the target consultation request and matching the keywords.
Optionally, in the information processing method provided by the embodiment of the present application, a plurality of history consultation information is stored in a history database, where each history consultation information is associated with a processing result, user information of a user who sends each history consultation information, and an information tag, where the information tag is used to characterize a consultation type of the plurality of history consultation information, and before acquiring N history consultation information stored in the history database, the step of acquiring N history consultation information stored in the history database is performed according to the information tag of the plurality of history consultation information.
Specifically, since the advisory information stored in the history database is associated with the information tag of the advisory type characterizing the history advisory information, the history advisory information can be determined in such a manner that the information tag of the target advisory information is matched with the information tag of each advisory information by acquiring the information tag of the advisory information stored in the history period and the information tag of the target advisory information when screening the history advisory information.
In addition, it should be noted that, each consultation information in the history database also stores basic information such as information submitters, submission time, submission channels, information fields, and information such as information processing schemes and processing result feedback.
In order to accurately send the target consultation information to the operation and maintenance personnel, optionally, in the information processing method provided by the embodiment of the present application, identifying the target consultation information to obtain the first information keyword includes: performing word segmentation processing on target consultation information to obtain M consultation words, and performing format conversion processing on the M consultation words to obtain M converted consultation words, wherein M is a positive integer; acquiring a preset vocabulary list, inputting the preset vocabulary list and M converted consultation words into a deep learning network model to obtain a recognition result, wherein the deep learning network model is used for carrying out text recognition processing on the M converted consultation words, and the preset vocabulary list comprises a plurality of preset types of vocabularies; under the condition that the recognition result represents that the M converted consultation words do not contain various vocabularies of preset types, determining target consultation information as safety information, and screening information keywords from the M converted consultation words to obtain first information keywords; and stopping executing the step of sending the target consultation request to the target client used by the operation and maintenance personnel according to the first information keyword under the condition that the recognition result represents that the M converted consultation words contain a plurality of preset types.
Specifically, if the similarity between the target consultation information and the candidate consultation information is low, it indicates that the target consultation request has no similar request sent by the user in the historical time period, the target consultation request can be sent to the operation and maintenance personnel, and the information keywords can be extracted from the target consultation information before the request is sent. Firstly, target consultation information is required to be subjected to word segmentation processing, the target consultation information is divided into single words to obtain a plurality of consultation words, and then format conversion processing is carried out on the consultation words, so that the consultation words accord with the input requirement of a deep learning network model, and a plurality of converted consultation words are obtained.
When the deep learning network model is utilized to carry out text recognition, a preset vocabulary list containing vocabularies of preset types such as violating science is firstly obtained, then the preset vocabulary list and the converted consultation words are input into the deep learning network model, and the deep learning network model is utilized to carry out text recognition processing, so that a recognition result is obtained. If the recognition result represents that the target consultation information does not contain the vocabulary in the preset vocabulary list, the target consultation information is indicated to be safety information, and information keywords can be screened out from the converted consultation words, so that first information keywords which can help understanding the requirements of users are obtained; if the recognition result represents that the target consultation information contains the vocabulary in the preset vocabulary list, the target consultation information is indicated to be unsafe information, the information keyword extraction processing cannot be performed on the target consultation information, and meanwhile, the target consultation request cannot be sent to operation and maintenance personnel. According to the embodiment, the text recognition processing of the target consultation information is performed by utilizing the deep learning network model, so that a foundation is laid for subsequently sending the target consultation request.
In order to improve accuracy of text recognition, optionally, in the information processing method provided by the embodiment of the present application, a deep learning network model is obtained through training: acquiring a preset deep learning network model, acquiring Y pieces of historical consultation information and historical recognition results related to the Y pieces of historical consultation information from a historical database, and combining the Y pieces of historical consultation information and the Y pieces of historical recognition results to obtain a training information set, wherein Y is a positive integer; training a preset deep learning network model by using a training information set to obtain a trained deep learning network model; acquiring the recognition accuracy associated with the trained deep learning network model, and under the condition that the recognition accuracy is smaller than or equal to the preset accuracy, performing parameter adjustment on the trained deep learning network model by utilizing an optimization algorithm until the recognition accuracy of the adjusted deep learning network model is larger than the preset accuracy, and determining the adjusted deep learning network model as the deep learning network model.
Specifically, before text recognition processing is performed using the deep learning network model, the deep learning network model needs to be sufficiently trained and adjusted using the history data. Firstly, the historical consultation information and the information keywords (namely the first information keywords) associated with each historical consultation information in the historical database can be obtained to construct a complete training information set, so that the model can be trained and optimized by using the training information set. After training, the recognition accuracy of the model is obtained, when the recognition accuracy is smaller than or equal to the preset accuracy, the recognition accuracy of the trained deep learning network model does not reach the preset accuracy, the trained deep learning network model needs to be adjusted until the recognition accuracy associated with the adjusted deep learning network model is larger than the preset accuracy, and the adjusted deep learning network model is determined to be the deep learning network model.
It should be noted that, when the parameter adjustment is performed on the trained deep learning network model, the parameter adjustment may be performed by using an optimization algorithm until the accuracy of the model reaches a preset requirement, so as to further improve the accuracy and generalization capability of the model, so as to better adapt to different types of target consultation requests, where the deep learning network model may be a convolutional neural network model, a cyclic neural network model, and the like. According to the embodiment, the deep learning network model is trained, so that the requirements of practical application are better met, and a foundation is laid for accurately identifying the text.
Optionally, in the information processing method provided by the embodiment of the present application, sending the target consultation request to the target client used by the operation and maintenance personnel according to the first information keyword includes: acquiring a candidate operation and maintenance personnel list, and screening information of target operation and maintenance personnel from the candidate operation and maintenance personnel list according to a first information keyword, wherein the candidate operation and maintenance personnel list comprises information of Z operation and maintenance personnel, and Z is a positive integer; and determining a target client according to the information of the target operation and maintenance personnel, and sending a target consultation request to the target client.
Specifically, when the history database does not store history consultation information of a consultation type similar to that of the target consultation information, the target consultation request needs to be transmitted to the relevant operation and maintenance personnel, and when the request is transmitted, the operation and maintenance personnel can be screened. Firstly, a list of operation and maintenance personnel capable of processing the consultation request can be obtained, a candidate operation and maintenance personnel list is obtained, and then information of operation and maintenance personnel capable of processing the target consultation request is screened out from the candidate operation and maintenance personnel list according to a first information keyword extracted from the target consultation request, and the information of the target operation and maintenance personnel is obtained. Further, the client used by the target operation and maintenance personnel (namely the target client) is determined according to the information of the target operation and maintenance personnel, and finally the target consultation request is sent to the target client, so that the processing efficiency and the accuracy of the consultation request can be improved.
Optionally, in the information processing method provided by the embodiment of the present application, after sending the target consultation request to the target client used by the operation and maintenance personnel according to the first information keyword, the method further includes: receiving a processing result fed back by operation and maintenance personnel through a target client; and packaging the processing result, the target consultation information and the user information of the user, and storing the packaged information into a history database.
Specifically, after the target consultation request is sent to the relevant operation and maintenance personnel, the operation and maintenance personnel process the target consultation request to obtain a processing result, and the processing result is returned to the information collection system associated with the financial institution. After the information collecting system receives the processing result, in order to provide the suggestion of the processing result of the consultation request for other users later, the returned processing result, the target consultation information and the user information of the proposer (namely, the user who sends the target consultation request) can be packaged, and the packaged information is stored in the history database. According to the method and the device, the relevant information of the target consultation request is stored, so that effective advice can be timely provided when other users send out the consultation request later.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment of the application also provides an information processing device, and the information processing device of the embodiment of the application can be used for executing the information processing method provided by the embodiment of the application. The following describes an information processing apparatus provided by an embodiment of the present application.
Fig. 3 is a schematic diagram of an information processing apparatus according to an embodiment of the present application, as shown in fig. 3, the apparatus includes: a first receiving unit 30, an acquiring unit 31, a determining unit 32, and an identifying unit 33.
The first receiving unit 30 is configured to receive a target consultation request sent by a user through a client, identify the target consultation request, and obtain target consultation information;
an obtaining unit 31, configured to obtain candidate advisory information associated with the target advisory information from the history database, and calculate similarity data between the candidate advisory information and the target advisory information, so as to obtain information similarity;
A determining unit 32, configured to determine candidate advisory information as matching advisory information if the information similarity is greater than the similarity threshold, obtain a processing result associated with the matching advisory information, and send the processing result to the client;
the identifying unit 33 is configured to identify the target consultation information to obtain a first information keyword when the information similarity is less than or equal to a similarity threshold, and send a target consultation request to a target client used by the operation and maintenance personnel according to the first information keyword, where the first information keyword is used for screening the operation and maintenance personnel.
According to the information processing device provided by the embodiment of the application, the first receiving unit 30 receives the target consultation request sent by the user through the client, and identifies the target consultation request to obtain target consultation information; the obtaining unit 31 obtains candidate consulting information associated with the target consulting information from the history database, and calculates similarity data of the candidate consulting information and the target consulting information to obtain information similarity; the determining unit 32 determines candidate consulting information as matching consulting information in the case that the information similarity is greater than the similarity threshold, acquires a processing result associated with the matching consulting information, and transmits the processing result to the client; the identifying unit 33 identifies target consultation information to obtain a first information keyword under the condition that the information similarity is smaller than or equal to a similarity threshold, sends a target consultation request to a target client used by operation staff according to the first information keyword, wherein the first information keyword is used for screening the operation staff, solves the problem that the accuracy of the provided processing result is low when the processing result of the target consultation request is provided for a user in the related art, obtains the target consultation information by identifying the target consultation request sent by the user through the client, calculates similarity data of candidate consultation information and the target consultation information obtained from a historical database to obtain information similarity, sends the processing result associated with the candidate consultation information to the client under the condition that the information similarity is smaller than or equal to the similarity threshold, and sends the target consultation request to the target client used by the operation staff, thereby achieving the effect of improving the accuracy of the provided processing result.
Alternatively, in the information processing apparatus provided by the embodiment of the present application, the acquisition unit 31 includes: the first processing module is used for preprocessing the target consultation information to obtain initial processing information, wherein the preprocessing mode at least comprises one of the following steps: data cleaning and format conversion; the extraction module is used for extracting information keywords from the initial processing information to obtain a group of second information keywords, wherein the group of second information keywords refer to words representing the consultation contents in the target consultation request; the first acquisition module is used for acquiring N pieces of historical consultation information stored in the historical database, extracting keywords of the N pieces of historical consultation information and obtaining N groups of third information keywords, wherein N is a positive integer; the calculation module is used for calculating the similarity between a group of second information keywords and each group of third information keywords to obtain N pieces of keyword similarity data, acquiring historical consultation information associated with the keyword similarity data with the largest numerical value, and determining the historical consultation information as candidate consultation information.
Alternatively, in the information processing apparatus provided by the embodiment of the present application, the identifying unit 33 includes: the second processing module is used for carrying out word segmentation processing on the target consultation information to obtain M consultation words, and carrying out format conversion processing on the M consultation words to obtain M converted consultation words, wherein M is a positive integer; the second acquisition module is used for acquiring a preset vocabulary list, inputting the preset vocabulary list and M converted consultation words into the deep learning network model to obtain a recognition result, wherein the deep learning network model is used for carrying out text recognition processing on the M converted consultation words, and the preset vocabulary list contains a plurality of preset types of vocabularies; the first determining module is used for determining target consultation information as safety information under the condition that the recognition result represents that the M converted consultation words do not contain various vocabularies of preset types, and screening information keywords from the M converted consultation words to obtain first information keywords; and the execution module is used for stopping executing the step of sending the target consultation request to the target client used by the operation and maintenance personnel according to the first information keyword under the condition that the recognition result represents that the M converted consultation words contain a plurality of preset types.
Alternatively, in the information processing apparatus provided by the embodiment of the present application, the identifying unit 33 includes: the deep learning network model is obtained through training the following steps: the third acquisition module is used for acquiring a preset deep learning network model, acquiring Y pieces of historical consultation information and historical recognition results related to the Y pieces of historical consultation information from a historical database, and combining the Y pieces of historical consultation information and the Y pieces of historical recognition results to obtain a training information set, wherein Y is a positive integer; the training module is used for training the preset deep learning network model by utilizing the training information set to obtain a trained deep learning network model; and the fourth acquisition module is used for acquiring the recognition accuracy associated with the trained deep learning network model, and carrying out parameter adjustment on the trained deep learning network model by utilizing an optimization algorithm under the condition that the recognition accuracy is smaller than or equal to the preset accuracy until the recognition accuracy of the adjusted deep learning network model is larger than the preset accuracy, and determining the adjusted deep learning network model as the deep learning network model.
Alternatively, in the information processing apparatus provided by the embodiment of the present application, the identifying unit 33 includes: a fifth obtaining module, configured to obtain a candidate operation and maintenance personnel list, and screen information of a target operation and maintenance personnel from the candidate operation and maintenance personnel list according to a first information keyword, where the candidate operation and maintenance personnel list includes information of Z operation and maintenance personnel, and Z is a positive integer; and the second determining module is used for determining a target client according to the information of the target operation and maintenance personnel and sending the target consultation request to the target client.
Optionally, in the information processing apparatus provided in the embodiment of the present application, the apparatus further includes: the second receiving unit is used for receiving a processing result fed back by the operation and maintenance personnel through the target client after the target consultation request is sent to the target client used by the operation and maintenance personnel according to the first information keyword; and the packaging unit is used for packaging the processing result, the target consultation information and the user information of the user and storing the packaged information into the history database.
Alternatively, in the information processing apparatus provided by the embodiment of the present application, the identifying unit 33 includes: the method comprises the steps of storing a plurality of historical consultation information in a historical database, wherein each historical consultation information is associated with a processing result, user information of a user sending out each historical consultation information and an information label, the information label is used for representing the consultation type of the plurality of historical consultation information, acquiring the information label of the plurality of historical consultation information before acquiring N pieces of the historical consultation information stored in the historical database, and executing the step of acquiring the N pieces of the historical consultation information stored in the historical database according to the information label of the plurality of historical consultation information.
The information processing apparatus includes a processor and a memory, and the first receiving unit 30, the acquiring unit 31, the determining unit 32, the identifying unit 33, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize the corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be set with one or more than one, and the problem of low accuracy of the provided processing result when the processing result of the target consultation request is provided for the user in the related technology is solved by adjusting the kernel parameters.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
The embodiment of the invention provides a computer storage medium which is used for storing a program, wherein the program is used for controlling equipment where the computer storage medium is located to execute an information processing method when running.
Fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 4, an electronic device 40 is provided, where the electronic device 40 includes a processor, a memory, and a program stored on the memory and executable on the processor, and the processor is configured to execute computer readable instructions, where the computer readable instructions execute a method for processing information when executed. The device herein may be a server, PC, PAD, cell phone, etc.
The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of a method for processing information in various embodiments of the application.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The collected information is information and data authorized by a user or fully authorized by each party, and the processing of collection, storage, use, processing, transmission, provision, disclosure, application and the like of the related data all obeys the related laws and regulations and standards of the related region, necessary security measures are taken without violating the public welfare, and corresponding operation entrance is provided for the user to select authorization or rejection.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. A method of processing information, comprising:
receiving a target consultation request sent by a user through a client, and identifying the target consultation request to obtain target consultation information;
candidate consultation information associated with the target consultation information is obtained from a historical database, similarity data of the candidate consultation information and the target consultation information are calculated, and information similarity is obtained;
Under the condition that the information similarity is larger than a similarity threshold, determining the candidate consultation information as matched consultation information, acquiring a processing result associated with the matched consultation information, and sending the processing result to the client;
And under the condition that the information similarity is smaller than or equal to the similarity threshold, identifying the target consultation information to obtain a first information keyword, and sending the target consultation request to a target client used by operation and maintenance personnel according to the first information keyword, wherein the first information keyword is used for screening the operation and maintenance personnel.
2. The method of claim 1, wherein retrieving candidate advisory information associated with the target advisory information from a historical database comprises:
Preprocessing the target consultation information to obtain initial processing information, wherein the preprocessing mode at least comprises one of the following steps: data cleaning and format conversion;
Extracting information keywords from the initial processing information to obtain a group of second information keywords, wherein the group of second information keywords refer to words representing the consultation contents in the target consultation request;
Acquiring N pieces of history consultation information stored in the history database, and extracting keywords of the N pieces of history consultation information to obtain N groups of third information keywords, wherein N is a positive integer;
And calculating the similarity of the group of second information keywords and each group of third information keywords to obtain N pieces of keyword similarity data, obtaining historical consultation information associated with the keyword similarity data with the largest numerical value, and determining the historical consultation information as the candidate consultation information.
3. The method of claim 1, wherein identifying the target advisory information to obtain the first information keyword comprises:
performing word segmentation processing on the target consultation information to obtain M consultation words, and performing format conversion processing on the M consultation words to obtain M converted consultation words, wherein M is a positive integer;
A preset vocabulary list is obtained, the preset vocabulary list and the M converted consultation words are input into a deep learning network model, and a recognition result is obtained, wherein the deep learning network model is used for carrying out text recognition processing on the M converted consultation words, and the preset vocabulary list contains a plurality of preset types of vocabularies;
Under the condition that the recognition result characterizes that the M converted consultation words do not contain the words of the multiple preset types, determining the target consultation information as safety information, and screening information keywords from the M converted consultation words to obtain the first information keywords;
and stopping executing the step of sending the target consultation request to a target client used by operation and maintenance personnel according to the first information keyword under the condition that the recognition result characterizes that the M converted consultation words contain the plurality of preset types.
4. A method according to claim 3, wherein the deep learning network model is trained by:
Acquiring a preset deep learning network model, acquiring Y pieces of historical consultation information and historical recognition results related to the Y pieces of historical consultation information from the historical database, and combining the Y pieces of historical consultation information and the Y pieces of historical recognition results to obtain a training information set, wherein Y is a positive integer;
Training the preset deep learning network model by using the training information set to obtain a trained deep learning network model;
Acquiring the recognition accuracy associated with the trained deep learning network model, and under the condition that the recognition accuracy is smaller than or equal to a preset accuracy, performing parameter adjustment on the trained deep learning network model by using an optimization algorithm until the recognition accuracy of the adjusted deep learning network model is larger than the preset accuracy, and determining the adjusted deep learning network model as the deep learning network model.
5. The method of claim 1, wherein transmitting the target consultation request to a target client for use by an operation and maintenance person according to the first information keyword comprises:
Acquiring a candidate operation and maintenance personnel list, and screening information of target operation and maintenance personnel from the candidate operation and maintenance personnel list according to the first information keyword, wherein the candidate operation and maintenance personnel list comprises information of Z operation and maintenance personnel, and Z is a positive integer;
and determining the target client according to the information of the target operation and maintenance personnel, and sending the target consultation request to the target client.
6. The method of claim 5, wherein after the target consultation request is sent to the target client for use by the operation and maintenance personnel according to the first information keyword, the method further comprises:
Receiving a processing result fed back by the operation and maintenance personnel through the target client;
And packaging the processing result, the target consultation information and the user information of the user, and storing the packaged information into the history database.
7. The method according to claim 2, wherein a plurality of history consultation information is stored in the history database, wherein each history consultation information is associated with a processing result, user information of a user who issues each history consultation information, and an information tag for characterizing a consultation type of the plurality of history consultation information, the information tag of the plurality of history consultation information is acquired before the N history consultation information stored in the history database is acquired, and the step of acquiring the N history consultation information stored in the history database is performed according to the information tag of the plurality of history consultation information.
8. An information processing apparatus, comprising:
The first receiving unit is used for receiving a target consultation request sent by a user through a client, identifying the target consultation request and obtaining target consultation information;
The acquisition unit is used for acquiring candidate consultation information associated with the target consultation information from the historical database, and calculating similarity data of the candidate consultation information and the target consultation information to obtain information similarity;
the determining unit is used for determining the candidate consultation information as matched consultation information under the condition that the information similarity is larger than a similarity threshold value, acquiring a processing result associated with the matched consultation information and sending the processing result to the client;
The identifying unit is used for identifying the target consultation information to obtain a first information keyword under the condition that the information similarity is smaller than or equal to the similarity threshold value, and sending the target consultation request to a target client used by operation and maintenance personnel according to the first information keyword, wherein the first information keyword is used for screening the operation and maintenance personnel.
9. A computer storage medium for storing a program, wherein the program when run controls a device in which the computer storage medium is located to perform the method of processing information according to any one of claims 1 to 7.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of processing information of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410237692.5A CN118093626A (en) | 2024-03-01 | 2024-03-01 | Information processing method and device, computer storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410237692.5A CN118093626A (en) | 2024-03-01 | 2024-03-01 | Information processing method and device, computer storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118093626A true CN118093626A (en) | 2024-05-28 |
Family
ID=91152938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410237692.5A Pending CN118093626A (en) | 2024-03-01 | 2024-03-01 | Information processing method and device, computer storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118093626A (en) |
-
2024
- 2024-03-01 CN CN202410237692.5A patent/CN118093626A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109255499B (en) | Complaint and complaint case processing method, device and equipment | |
| CN110852894B (en) | Insurance verification method and apparatus, computer storage medium and electronic device | |
| US20180336272A1 (en) | Generation of natural language processing events using machine intelligence | |
| KR102496584B1 (en) | System for Real Estate Investment Analysis and Recommendation based on Customer's Requirements and Constraints by using Data Mining and Machine Learning | |
| US11182411B2 (en) | Combined data driven and knowledge driven analytics | |
| CN113762973A (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN116521871A (en) | File detection method and device, processor and electronic equipment | |
| CN118093626A (en) | Information processing method and device, computer storage medium and electronic equipment | |
| CN113723525B (en) | Product recommendation method, device, equipment and storage medium based on genetic algorithm | |
| KR102284440B1 (en) | Method to broker deep learning model transactions perfomed by deep learning model transaction brokerage servers | |
| CN113849618A (en) | Strategy determination method and device based on knowledge graph, electronic equipment and medium | |
| CN113742495A (en) | Rating characteristic weight determination method and device based on prediction model and electronic equipment | |
| Mahalle et al. | Data Acquisition and Preparation | |
| CN117172632B (en) | Enterprise abnormal behavior detection method, device, equipment and storage medium | |
| Anusha et al. | Big Data Quality-A Survey paper to attain Data quality | |
| KR102311108B1 (en) | Method to broker deep learning model transactions perfomed by deep learning model transaction brokerage servers | |
| KR102313181B1 (en) | Deep learning solution providing method performed by deep learning platform providing device that provides deep learning solution platform | |
| CN118115264A (en) | Risk identification method, risk identification device, electronic equipment and storage medium | |
| CN116523648A (en) | Risk object identification method and device, storage medium and electronic equipment | |
| CN118052632A (en) | Method and device for determining risk assessment model and computer readable storage medium | |
| CN117252362A (en) | Scheduling method and device based on artificial intelligence, computer equipment and storage medium | |
| CN116757832A (en) | Loan repayment risk prediction method, loan repayment risk prediction device and storage medium | |
| CN116756290A (en) | Data query method and device, storage medium and electronic equipment | |
| CN117407750A (en) | Metadata-based data quality monitoring method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |