CN-117171327-B - Data processing method, device and equipment and computer storage medium

CN117171327BCN 117171327 BCN117171327 BCN 117171327BCN-117171327-B

Abstract

The application provides a method, a device and equipment for processing data and a computer storage medium, wherein the method relates to the technical field of intelligent response, is applied to an intelligent response system, and comprises a machine response and a manual response; the input data comprises input data from a problem proposer and input data from a manual answering party, keyword detection is carried out on the input data based on a preset keyword set to obtain a corresponding target detection result, the target detection result comprises overall distribution information of target keyword data in the keyword set in the input data, if the target keyword data exist in the input data based on the target detection result, the appearance sequence of the target keyword data is obtained based on the overall distribution information, and the corresponding target answer data are respectively output to a source party of the input data based on the appearance sequence and in combination with a preset answer data set.

Inventors

WANG XIAOQIANG
LI ZHIFU

Assignees

中国建设银行股份有限公司
建信金融科技有限责任公司

Dates

Publication Date: 20260505
Application Date: 20230922

Claims (11)

1. A method of data processing, characterized by being applied to an intelligent response system including machine responses and manual responses, the method comprising: the input data received by the intelligent response system is obtained, wherein the input data comprises input data from a problem proposer and input data from a manual response party; Performing keyword detection on the input data based on a preset keyword set in combination with a time range determined based on the problem proposer and a time range determined based on the manual response party to obtain a corresponding target detection result, wherein the target detection result comprises overall distribution information of target keyword data in the keyword set in the input data; if the target key data exist in the input data based on the target detection result, acquiring the appearance sequence of the target key data based on the overall distribution information; Based on the appearance sequence, combining a preset reply data set, and outputting corresponding target reply data to the problem proposer and the manual responder respectively; When the input data only comprises input data from a problem proposer, acquiring target times of occurrence of the target key data in the input data within a preset time range; Based on the target times, associating the question proposer with a corresponding emotion label; and before the artificial responder accesses the intelligent response system, transmitting an emotion tag associated with the problem proposer to the artificial responder.
2. The method of claim 1, wherein the outputting, based on the order of occurrence, corresponding target reply data to the question proposer and the manual responder, respectively, in combination with a preset reply data set, includes: acquiring the accumulated times of occurrence of the target key data in one input data within a preset time range based on the overall distribution information; And based on the appearance sequence and the accumulated times, acquiring target reply data corresponding to the appearance sequence and the accumulated times from the reply data set, and respectively outputting the corresponding target reply data to the problem proposer and the manual responder.
3. The method of claim 1, wherein after outputting corresponding target reply data to the question proposer and the manual responder, respectively, the method further comprises: Selecting input data without the target key data from the input data from the problem proposer as target input data, and storing the target input data to a preset storage address; and storing all the input data from the manual answering party to the preset storage address.
4. The method of claim 1, wherein prior to said obtaining input data received by said intelligent answering system, said method further comprises: Acquiring at least one keyword; Converting the at least one keyword according to a preset format to obtain corresponding target key data, and storing the target key data into the keyword set.
5. A data processing apparatus for use in an intelligent response system, the intelligent response system including a machine response and a human response, the apparatus comprising: The system comprises an intelligent response system, an acquisition module and a control module, wherein the intelligent response system is used for receiving input data received by the intelligent response system, and the input data comprises input data from a problem proposer and input data from a manual response party; the processing module is used for carrying out keyword detection on the input data based on a preset keyword set and combining a time range determined based on the problem proposer and a time range determined based on the manual response party to obtain a corresponding target detection result, wherein the target detection result comprises overall distribution information of target keyword data in the keyword set in the input data; The output module is used for respectively outputting corresponding target reply data to the problem proposer and the manual responder by combining a preset reply data set based on the appearance sequence; When the input data only comprises input data from a question-presenting party, the processing module is further used for acquiring target times of occurrence of the target key data in the input data within a preset time range, associating the question-presenting party with a corresponding emotion label based on the target times, and transmitting the emotion label associated with the question-presenting party to the manual answering party before the manual answering party accesses the intelligent answering system.
6. The apparatus of claim 5, wherein the output module is configured to, based on the occurrence sequence, combine a preset reply data set, output corresponding target reply data to the question-presenting party and the manual answering party, respectively, and specifically configured to: acquiring the accumulated times of occurrence of the target key data in one input data within a preset time range based on the overall distribution information; And based on the appearance sequence and the accumulated times, acquiring target reply data corresponding to the appearance sequence and the accumulated times from the reply data set, and respectively outputting the corresponding target reply data to the problem proposer and the manual responder.
7. The apparatus of claim 5, further comprising a storage module for, after the output module is configured to output corresponding target reply data to the question-proposing party and the manual answering party, respectively: Selecting input data without the target key data from the input data from the problem proposer as target input data, and storing the target input data to a preset storage address; and storing all the input data from the manual answering party to the preset storage address.
8. The apparatus of claim 5, wherein prior to the acquiring the input data received by the intelligent answering system, the acquisition module is further to: Acquiring at least one keyword; Converting the at least one keyword according to a preset format to obtain corresponding target key data, and storing the target key data into the keyword set.
9. An electronic device, comprising: And a memory communicatively coupled to the at least one processor; Wherein the memory stores instructions executable by the at least one processor, by executing the instructions stored by the memory, causing the at least one processor to perform the method of any one of claims 1-4.
10. A computer readable storage medium for storing instructions that, when executed, cause the method of any one of claims 1-4 to be implemented.
11. A computer program product comprising instructions, characterized in that the computer program product has instructions stored therein, which, when run on a computer, cause the computer to perform the method according to any of claims 1-4.

Description

Data processing method, device and equipment and computer storage medium Technical Field The present application relates to the field of intelligent answering technologies, and in particular, to a method, an apparatus, and a device for data processing, and a computer storage medium. Background With the continuous development of internet technology, intelligent response is widely applied to various industries. The service provider presets the questions and corresponding answers in an intelligent response mode, so that when the user generates corresponding questions, the answers can be obtained rapidly in the intelligent response mode. However, in the general intelligent response process, the user's questions can only be mechanically replied according to the preset questions and answers, and the corresponding feedback can not be performed in time according to the change of the user's state, which can reduce the user experience, and further result in poor response effect provided by the intelligent response, and low efficiency of problem solving. Therefore, how to improve the response effect and the corresponding user experience in the intelligent response process is a problem to be solved urgently. Disclosure of Invention The application provides a data processing method, a device and equipment and a computer storage medium, which are used for improving the response effect and corresponding user experience in the intelligent response process. The embodiment of the application provides a data processing method, which is applied to an intelligent response system, wherein the intelligent response system comprises a machine response and a manual response, the method comprises the steps of obtaining input data received by the intelligent response system, wherein the input data comprise input data from a problem proposer and input data from a manual response party, conducting keyword detection on the input data based on a preset keyword set to obtain a corresponding target detection result, the target detection result comprises overall distribution information of target keyword data in the keyword set in the input data, and if the target keyword data are determined to exist in the input data based on the target detection result, obtaining the appearance sequence of the target keyword data based on the overall distribution information, and respectively outputting corresponding target response data to a source of the input data based on the appearance sequence in combination with the preset response data set. In the scheme, the keyword detection is carried out on the input data from the two parties of the problem proposer and the manual responder in the intelligent response system, the target detection result indicating the overall distribution information of the target keyword data is obtained, and according to the distribution condition of the target keyword data in the input data from the two parties of the problem proposer and the manual responder in the overall distribution information, the corresponding target response data are output to the parties in a targeted manner, so that the use experience of the two parties on the intelligent response system is improved, the possible emotion conflict can be relieved, and the efficiency of solving the problem of the problem proposer is effectively improved. On the other hand, the input data is identified by the target key data in the key word set, semantic analysis is not needed for the input data, and only whether the input data has characters identical to the target key data or not is judged, so that the response of the server to the target key data can be quickened, and the occupation of computing resources caused by the semantic analysis can be avoided. Optionally, the step of respectively outputting corresponding target reply data to the source side of the input data based on the appearance sequence and the preset reply data set comprises the steps of acquiring the accumulated times of the occurrence of the target key data in one input data within a preset time range based on the whole distribution information, acquiring the target reply data corresponding to the appearance sequence and the accumulated times from the reply data set based on the appearance sequence and the accumulated times, and outputting the target reply data to the source side. In the method, based on the occurrence sequence and the accumulated times of the target key data, different target reply data are selected to be respectively output to the problem proposer and the manual responder, so that the reply data are more targeted to different situations, the efficiency of relieving the current emotion conflict is further improved, and the use experience of both parties is improved. Optionally, after outputting the corresponding target reply data to the source side of the input data, the method further comprises selecting input data without the target key data as target input data from the problem