CN112380381A - Method and device for intelligently managing seats, robot and storage medium - Google Patents

Method and device for intelligently managing seats, robot and storage medium Download PDF

Info

Publication number
CN112380381A
CN112380381A CN202011275337.5A CN202011275337A CN112380381A CN 112380381 A CN112380381 A CN 112380381A CN 202011275337 A CN202011275337 A CN 202011275337A CN 112380381 A CN112380381 A CN 112380381A
Authority
CN
China
Prior art keywords
content
text data
time length
tag
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011275337.5A
Other languages
Chinese (zh)
Other versions
CN112380381B (en
Inventor
张亚南
杜新凯
吕超
王建辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sunshine Insurance Group Co Ltd
Original Assignee
Sunshine Insurance Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sunshine Insurance Group Co Ltd filed Critical Sunshine Insurance Group Co Ltd
Priority to CN202011275337.5A priority Critical patent/CN112380381B/en
Publication of CN112380381A publication Critical patent/CN112380381A/en
Application granted granted Critical
Publication of CN112380381B publication Critical patent/CN112380381B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/65—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/685—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using automatically derived transcript of audio data, e.g. lyrics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06398—Performance of employee with respect to a job function
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The application provides a method and a device for intelligently managing agents, a robot and a storage medium, and belongs to the technical field of computer information. The method comprises the steps of obtaining text data corresponding to a voice file of an agent, counting the number of content tags appearing and not appearing in a management index in the text data, counting the duration corresponding to each content tag in the text data, and obtaining a counting result, wherein the duration corresponding to each content tag is obtained according to time information corresponding to the content tag; carrying out quantitative preprocessing on the statistical result to obtain a corresponding quantitative index, wherein the quantitative index is used for representing the service capability of the seat; and executing preset management operation corresponding to the quantization index. This scheme of use can help the enterprise to realize the seat management that becomes more meticulous, automatic, and then saves the cost of enterprise, promotes enterprise competitiveness.

Description

Method and device for intelligently managing seats, robot and storage medium
Technical Field
The application relates to the technical field of computer information, in particular to a method and a device for intelligently managing an agent, a robot and a storage medium.
Background
In the fields of sales, customer service and the like, enterprises often arrange a large number of seats to actively or passively contact customers in the form of telephones to develop services or marketing activities. In the prior art, a method for managing the seat according to indexes such as the number of calls, the call duration, the end code and the like of the seat is very extensive, and enterprises cannot master the service capacity or the sales capacity of the seat through the method, so that fine management cannot be performed according to the capacity of the seat. Meanwhile, enterprises need a large number of managers to manage the seats, so that the labor cost of the enterprises is greatly increased, and great burden is caused to the enterprises.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for intelligently managing an agent, a robot, and a storage medium, so as to help an enterprise realize refined and automated agent management.
In a first aspect, an embodiment of the present application provides a method for intelligently managing agents, including: acquiring text data corresponding to a voice file of an agent, wherein the text data comprises content labels obtained by classifying according to preset management indexes and time information corresponding to each content label in the voice file; counting the number of content tags appearing in the text data and not appearing in the management index, and counting the duration corresponding to each content tag in the text data to obtain a counting result, wherein the duration corresponding to each content tag is obtained according to the time information corresponding to the content tag; carrying out quantitative preprocessing on the statistical result to obtain a corresponding quantitative index, wherein the quantitative index is used for representing the service capability of the seat; and executing preset management operation corresponding to the quantization index.
In the embodiment of the application, the service capacity of the seat can be mastered by enterprises through the quantitative indexes corresponding to the seat, and the seat is directly managed through preset management operation, so that the number of managers is reduced, and the labor cost of the enterprises is saved.
With reference to the technical solution provided by the first aspect, in some possible implementation manners, the text data includes a plurality of text data, and counting the number of content tags that appear in the text data and do not appear in the management index includes: for each text data, the number of content tags in the text data that do not appear in the management index is recorded as 0, and the number of content tags that appear in the management index is recorded as 1.
In the embodiment of the present application, when the number of content tags is counted, only whether the content tags appear in the management index is concerned, the number of content tags that do not appear in the management index in the text data is regarded as 0, and the number of content tags that appear in the management index is regarded as 1, without concerning the specific data thereof, which can avoid the influence of a plurality of identical content tags (because the same type of content is not necessarily continuous in one text data, a plurality of identical content tags may simultaneously exist in one text data) on the quantization index.
With reference to the technical solution provided by the first aspect, in some possible implementation manners, the text data includes a plurality of text data, each text data further includes an identifier representing an agent, and the statistical result performs quantization preprocessing on the statistical result to obtain a corresponding quantization index, including: quantifying the time length corresponding to each content tag contained in the statistical result, and recording the time length corresponding to the content tag with the time length being greater than or equal to a preset threshold time length as 1 and recording the time length corresponding to the content tag with the time length being less than the threshold time length as 0; aggregating the statistical results which have the same seat identification and quantify the time length corresponding to the content label to obtain the total number of each content label and the total number of each content label with the time length reaching the standard; and calculating the occupation ratio of each content label and the time length standard-reaching rate of each content label aiming at each aggregation result, wherein the total number of each content label, the time length standard-reaching total number of each content label, the occupation ratio of each content label and the time length standard-reaching rate of each content label are quantitative indexes corresponding to the seat.
In the embodiment of the application, when the quantitative index of the agent is obtained, the time length corresponding to each content tag contained in the statistical result is quantized, then the statistical results with the same agent identifier are aggregated to obtain the total number of each content tag and the total number of the time length of each content tag reaching the standard, then the proportion of each content tag and the time length reaching rate of each content tag are calculated according to each aggregation result, and the total number of each content tag, the total number of the time length of each content tag reaching the standard, the proportion of each content tag and the time length reaching rate of each content tag under the agent are integrated to serve as the quantitative index representing the service capability of the agent, so that the service capability of the agent can be reflected more accurately and objectively.
With reference to the technical solution provided by the first aspect, in some possible implementation manners, the text data includes a plurality of pieces of text data, each piece of text data includes an identifier representing an agent and timestamp information, and the statistical result is subjected to quantization preprocessing to obtain a corresponding quantization index, including: quantifying the time length corresponding to each content tag contained in the statistical result, and recording the time length corresponding to the content tag with the time length being greater than or equal to a preset threshold time length as 1 and recording the time length corresponding to the content tag with the time length being less than the threshold time length as 0; aggregating statistical results obtained after the timestamp information is in a preset time period and has the same seat identification and the time length corresponding to the content tags is quantified to obtain the total number of each content tag in the preset time period and the total number of each content tag reaching the standard in the preset time period; and calculating the proportion of each content label in the preset time period and the time standard-reaching rate of each content label in the preset time period aiming at each aggregation result, wherein the total number of each content label in the preset time period, the total number of each content label in the preset time period for reaching the time standard, the proportion of each content label in the preset time period, and the time standard-reaching rate of each content label in the preset time period are corresponding quantitative indexes of the seat in the preset time period.
In the embodiment of the application, when a quantization index of an agent is obtained, firstly, a time length corresponding to each content tag contained in a statistical result is quantized, then, timestamp information has the same agent identifier within a preset time period, and the statistical results obtained after the time length corresponding to the content tags is quantized are aggregated to obtain a total number of each content tag within the preset time period and a total number of each content tag reaching the standard within the preset time period, then, for each aggregation result, a proportion of each content tag within the preset time period and a time length reaching rate of each content tag within the preset time period are calculated, and the total number of each content tag within the preset time period, the proportion of each content tag within the preset time period and the time length reaching rate of each content tag within the preset time period are integrated to represent the agent as a representation of the agent within the preset time period The quantitative index of the service capability in the seat can more intuitively, accurately and objectively reflect the service capability of the seat in a preset time period.
With reference to the technical solution provided by the first aspect, in some possible implementation manners, before the text data is acquired, the method further includes: acquiring a voice file; performing voice recognition on the voice file to obtain initial text data, wherein each sentence in the initial text data corresponds to time information; preprocessing the initial text data to obtain text data; classifying the contents in the data according to preset management indexes to obtain content labels corresponding to classification categories; and for each content tag, determining the time information of each sentence included in the content tag, which corresponds to the content tag in the voice file.
In the embodiment of the application, the acquired voice file is processed in advance to obtain the text data containing the content tag and the time information corresponding to the content tag in the voice file, so that the subsequent statistics and quantitative preprocessing are facilitated, and the subsequent management efficiency is accelerated.
With reference to the technical solution provided by the first aspect, in some possible implementation manners, the preprocessing the initial text data includes: selecting text data belonging to the seat from the initial text data; and adding identification representing the agent and timestamp information in the text data belonging to the agent.
In the embodiment of the application, the selected text data belonging to the agent can reduce the workload of classifying the text data, and meanwhile, the text data of the served party is prevented from influencing the classification; and the identifier and the timestamp information which represent the seat are added, so that the time information and the seat information can be provided by performing statistics and quantitative preprocessing according to the time and/or the dimension of the seat in the subsequent statistics and quantitative preprocessing.
With reference to the technical solution provided by the first aspect, in some possible implementation manners, the obtaining a voice file includes: and converting the format of the obtained initial voice file into a preset standard format to obtain the voice file.
In the embodiment of the application, the format of the initial voice file is converted into the preset standard format, so that the voice file can be converted into the text data in the following process conveniently, the formats of the voice files in different formats are the same, and the time consumption caused by different formats in the following process can be saved.
In a second aspect, an embodiment of the present application provides an apparatus for intelligently managing an agent, including: the device comprises an acquisition module, a statistic module, a processing module and a management module. The acquiring module is used for acquiring text data corresponding to a voice file of the agent, wherein the text data comprises content labels obtained by classifying according to preset management indexes and time information corresponding to each content label in the voice file; the statistical module is used for counting the number of the content tags appearing in the text data and not appearing in the management index and counting the duration corresponding to each content tag in the text data to obtain a statistical result, wherein the duration corresponding to each content tag is obtained according to the time information corresponding to the content tag; the processing module is used for carrying out quantitative preprocessing on the statistical result to obtain a corresponding quantitative index, and the quantitative index is used for representing the service capability of the seat; the management module is used for executing preset management operation corresponding to the quantization index.
In a third aspect, an embodiment of the present application provides a robot, including a memory and a processor, where the memory is connected to the processor; the memory is used for storing programs; the processor is configured to invoke a program stored in the memory to perform the method according to the embodiment of the first aspect and/or any possible implementation manner in combination with the embodiment of the first aspect.
In a fourth aspect, embodiments of the present application provide a storage medium, on which a computer program is stored, where the computer program is executed to perform the method as described in the foregoing first aspect embodiment and/or any possible implementation manner in combination with the first aspect embodiment.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a method for intelligently managing agents according to an embodiment of the present disclosure;
fig. 2 is a block diagram illustrating a structure of an apparatus for intelligently managing an agent according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a robot according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
In the description of the present application, it should be noted that the terms "inside", "outside", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings or orientations or positional relationships that the products of the application usually place when using, and are only used for convenience in describing the present application and simplifying the description, but do not indicate or imply that the devices or elements that are referred to must have a specific orientation, be constructed in a specific orientation, and operate, and thus, should not be construed as limiting the present application. Furthermore, the terms "first," "second," and the like are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
It should also be noted that, unless expressly stated or limited otherwise, the terms "disposed" and "connected" are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
Please refer to fig. 1, which is a method for intelligently managing agents according to an embodiment of the present application, and the steps included in the method are described below with reference to fig. 1.
S100: and acquiring text data corresponding to the voice file of the agent, wherein the text data comprises content labels obtained by classifying according to preset management indexes and time information corresponding to each content label in the voice file.
The text data corresponding to the acquired voice file of the agent may be prepared in advance, and may be directly acquired when necessary. In one embodiment, before obtaining text data corresponding to a voice file of an agent, the method further includes: the method comprises the steps of obtaining a voice file of a call between a seat and a client (served party), carrying out voice recognition on the obtained voice file to obtain initial text data, preprocessing the initial text data to obtain text data, classifying contents in the data according to preset management indexes to obtain content labels corresponding to classification types, and finally determining time information of each content label corresponding to the voice file according to time information of each statement in the content label. Optionally, the acquired voice file may also be a voice file for customer service and sale.
In this embodiment, first, a speech file is recognized by a speech recognition technique to obtain initial text data, where each sentence in the initial text data corresponds to a time information, and the time information includes a start time and an end time of a speech information corresponding to the sentence in the speech file, for example, a speech information corresponding to a first sentence in the initial text data in the speech file is 0 to 10 seconds, and a time information corresponding to the first sentence is 0 to 10 seconds. Optionally, the process of acquiring the voice file may be: the method comprises the steps of firstly obtaining an initial voice file, and then converting the format of the obtained initial voice file into a preset standard format, so as to obtain the voice file, wherein the format of the initial voice file comprises a coding format, bit width and sampling rate. That is, in this embodiment, the voice file is a voice file whose format is converted into a predetermined standard format. Wherein, the preset standard format may be: the encoding format adopts wav (WaveForm file) format, the bit width adopts 16 bits, and the sampling rate adopts 8 KHz.
After the initial text data is obtained, the initial text data is preprocessed, for example, one embodiment of preprocessing the initial text data is to select text data belonging to an agent from the initial text data, and add identification and timestamp information representing the agent to the text data belonging to the agent. For example, through a natural language processing technology, the role recognition is performed on text data, the content of the text data is split into content corresponding to an agent and content corresponding to a served party, the text data belonging to the agent is selected, an identifier and timestamp information for representing the agent are added to the text data belonging to the agent, the identifier for representing the agent may include information of the agent, information of a team to which the agent belongs, and information of a region where the agent is located, and the timestamp information may be generated according to the time for generating the text data belonging to the agent, or generated according to time information carried by a voice file corresponding to the text data, or generated according to the time for acquiring the voice file corresponding to the text data. Optionally, the preprocessing of the initial text data further includes performing spelling error correction, word segmentation, sentence segmentation, and the like on the text data, then selecting the text data belonging to the seat on the basis, and adding a mark and timestamp information representing the seat in the text data belonging to the seat, that is, performing spelling error correction and word segmentation, sentence segmentation on the initial text data, then selecting the text data belonging to the seat from the initial text data subjected to the spelling error correction and word segmentation, sentence segmentation, and adding a mark and timestamp information representing the seat in the text data belonging to the seat. Wherein the spell correction comprises correcting spelling errors occurring in the initial text data. The word segmentation and sentence segmentation comprises the step of segmenting the content of the initial text data according to grammatical rules and semantics, so that the content of the initial text data conforms to the reading habit of ordinary people.
Then, based on the natural language processing technology, the text data is analyzed, and the content of the analysis is determined according to the preset management index, for example, in one case, the content of the analysis determined according to the preset management index includes: and analyzing the contents of the opening text, the service introduction, the service content, the closing words and the like in the text data. Based on the natural language processing technology, the text data is analyzed, the content of the text data is divided into four categories, namely, a field opening, service introduction, service content and a finish language, and the content corresponding to each category is labeled with the content label corresponding to the category. For example, the part of the text data belonging to the open space is labeled with a label representing the open space, such as a; the part belonging to the service introduction is marked with a label for representing the service introduction, such as B; the part belonging to the service content is marked with a label for representing the service content, such as C; the parts belonging to the closing word are labeled with a label characterizing the closing word, such as D. And finally, for each content tag, determining the time information corresponding to the content tag in the voice file according to the time information of each statement included in the content tag. For example, the open field white tag includes a first sentence and a second sentence in the text data, the time information corresponding to the first sentence is 0 to 10 seconds, the time information corresponding to the second sentence is 10 to 20 seconds, and the time duration corresponding to the open field white tag is 0 to 20 seconds. This example is merely one embodiment of the present application and is not intended to limit the present application. It should be noted that the type of the content tag may be formulated according to the requirement of the user, for example, the seat for selling the car insurance by telephone is managed, and the length of time when the seat is left on the spot, the type of the introduced product, and the customer price objection processing may be used as the classified or labeled content; the agent for telephone service customer is managed, and whether the agent appeals to complain customer, whether the introduction service is accurate, and whether the recommended business network is suitable can be used as classification or marking content.
S200: and counting the number of the content tags which appear in the text data and do not appear in the management index, and counting the duration corresponding to each content tag in the text data to obtain a counting result, wherein the duration corresponding to each content tag is obtained according to the time information corresponding to the content tag.
In an alternative embodiment, when the number of content tags appearing in the text data and not appearing in the management index is counted as 0, the number of content tags appearing in the management index is counted as 1, and the number of content tags appearing in the management index is counted as 0 even if the same content tag appears many times, as long as the content tag does not appear in the management index, and similarly, the number of content tags appearing in the management index is counted as 1 regardless of the number of occurrences. In one embodiment, the text data corresponding to the voice file of the agent includes a plurality of text data, and the number of content tags which appear in each text data and do not appear in the management index is counted. One embodiment of the statistics is to record, for each text data, the number of content tags that do not appear in the management index in the text data as 0, and the number of content tags that appear in the management index as 1; and calculating the time length corresponding to each content tag according to the time information corresponding to each content tag, and recording the time length of the content tag which does not appear as 0. For example, in the text data corresponding to one voice file, 1 open field white tag, 2 service introduction tags, and 1 service content tag are included, time information corresponding to the open field white tag is 0 to 20 seconds, time information corresponding to the service introduction tags is 20 to 50 seconds, 100 to 120 seconds, and time information corresponding to the service content tags is 50 to 100 seconds, and then in the statistical result of the text data, the open field white tag is marked as 1, the service introduction tag is marked as 1, the service content tag is marked as 1, the end word tag is marked as 0, the time length corresponding to the open field white tag is 20 seconds, the time length corresponding to the service introduction tag is 50 seconds, the time length corresponding to the service content tag is 50 seconds, and the time length corresponding to the end word tag is 0 second.
In another embodiment, for each text data, the number of content tags that do not appear in the management index in the text data is recorded as 0, and the total number of content tags that appear in the management index is recorded. For example, in the text data corresponding to one voice file, 1 open field white tag, 2 service introduction tags, and 1 service content tag are included, time information corresponding to the open field white tag is 0 to 20 seconds, time information corresponding to the service introduction tags is 20 to 50 seconds, 100 to 120 seconds, and time information corresponding to the service content tags is 50 to 100 seconds, and then in the statistical result of the text data, the open field white tag is marked as 1, the service introduction tag is marked as 2, the service content tag is marked as 1, the end word tag is marked as 0, the time length corresponding to the open field white tag is 20 seconds, the time length corresponding to the service introduction tag is 50 seconds, the time length corresponding to the service content tag is 50 seconds, and the time length corresponding to the end word tag is 0 second.
S300: and carrying out quantitative preprocessing on the statistical result to obtain a corresponding quantitative index, wherein the quantitative index is used for representing the service capability of the seat.
The quantitative preprocessing comprises counting, averaging, comparing, aggregating and other data processing methods, and the statistical results are processed through the counting, averaging, comparing, aggregating and other methods to generate quantitative indexes. Note that, when the quantization preprocessing is performed, only a part of the counting, averaging, comparison, and aggregation may be used, but not all of them. For example, in one embodiment, the number of the text data is multiple, each text data further includes an identifier representing an agent, a statistical result is generated from the multiple text data, the statistical result includes the identifier representing the agent, and the identifier representing the agent is used to mark data from the same text data as the identifier representing the agent in the statistical result. In one embodiment, the identifier representing the agent includes any one or any combination of multiple information of agent name, agent team information, agent number, and the like, or all information. The process of performing quantization preprocessing on the statistical result to obtain the corresponding quantization index may be: quantifying the time length corresponding to each content tag contained in the statistical result, recording the time length corresponding to the content tag with the time length being more than or equal to a preset threshold time length as 1, and recording the time length corresponding to the content tag with the time length being less than the threshold time length as 0; and then aggregating the statistical results which have the same seat identification and quantify the time length corresponding to the content labels to obtain the total number of each content label and the total number of the time length reaching the standard of each content label, and finally calculating the occupation ratio of each content label and the time length reaching rate of each content label aiming at each aggregated result. When comparing the duration corresponding to each content tag included in the statistical result with the duration threshold corresponding to the content tag, for example, in a statistical result generated from 5 text data, the number of open-field white tags is 1, 0, 1, and 1, the durations corresponding to the open-field white tags are 10 seconds, 20 seconds, 0 seconds, 5 seconds, and 15 seconds, wherein the first three statistical results (the number of open-field white tags is 1, and 0, the durations corresponding to the open-field white tags are 10 seconds, 20 seconds, and 0 seconds, respectively) have the same seat identifier x1, the last two statistical results (the number of open-field white tags is 1, and the durations corresponding to the open-field white tags are 5 seconds and 15 seconds, respectively) have the same seat identifier y1, the preset duration threshold is 15 seconds, and the first duration of the open-field white tags is 0, 1, 0, and 1, wherein, the mark 1 represents that the duration reaches the standard, and the mark 0 represents that the duration does not reach the standard.
And aggregating the statistical results which have the same agent identification and quantify the time length corresponding to the content labels to obtain the total number of each content label and the total number of each content label with the time length reaching the standard. As the above statistical results generated from the 5 text data items, where the first three statistical results (the number of open white tags is 1, and 0, and the durations corresponding to the open white tags are 10 seconds, 20 seconds, and 0 seconds, respectively) have the same seat identifier x1, and the last two statistical results (the number of open white tags is 1 and 1, and the durations corresponding to the open white tags are 5 seconds and 15 seconds, respectively) have the same seat identifier y1, then the aggregation result corresponding to x1 is: the number of the open field white labels is 2, and the total number of the time lengths corresponding to the open field white labels reaching the standard is 1; y1 corresponds to the polymerization result: the number of the open field white labels is 1, and the total number of the corresponding open field white labels reaching the standard is 1.
And then, for each aggregation result, calculating the proportion of each content label and the time length standard-reaching rate of each content label, taking the two aggregation results as an example, calculating the proportion of the open field white label in the aggregation result corresponding to x 1: 2/3 is obtained by the open field white label quantity/total item number of the statistical result; the time standard reaching rate of the open field white label is as follows: the total number of the time lengths corresponding to the open field white labels reaching the standard/the total number of the statistical results is 1/3; and (3) calculating the proportion of the open field white label in the polymerization result corresponding to y 1: 1/2 is obtained by the open field white label quantity/total item number of the statistical result; the time standard reaching rate of the open field white label is as follows: and the total number of the time lengths corresponding to the open field white labels reaching the standard/the total number of the statistical results is 1/2. And taking the obtained total number of each content label, the total number of the time length of each content label reaching the standard, the percentage of each content label and the time length reaching rate of each content label as the quantitative indexes of the seat. Taking the above two aggregation results and two calculation results as examples, we obtain quantization indexes for x1 and y1, where the quantization index for x1 is: the number of the open-field white labels is 2, the total number of the time length reaching the standard corresponding to the open-field white labels is 1, the proportion of the open-field white labels is 2/3, and the time length reaching rate of the open-field white labels is 1/3; the quantization index of y1 is: the number of the open-field white labels is 1, the total number of the time length reaching the standard corresponding to the open-field white labels is 1, the ratio of the open-field white labels is 1/2, and the time length reaching rate of the open-field white labels is 1/2. This example is merely one embodiment of the present application and is not intended to limit the present application.
In another embodiment, each of the plurality of text data further includes an identifier representing an agent and timestamp information, a statistical result is generated from the plurality of text data, the statistical result includes the identifier representing the agent and the timestamp information, the identifier representing the agent is used to mark data from the same text data as the identifier representing the agent in the statistical result, and the timestamp information is used to represent time from the same text data as the timestamp information in the statistical result. In one embodiment, the identifier representing the agent includes any one or any combination of multiple information of agent name, agent team information, agent employee number, and the like, or all information, and the timestamp information includes information of year, month, day, and the like. The process of performing quantization preprocessing on the statistical result to obtain the corresponding quantization index may be: quantifying the time length corresponding to each content tag contained in the statistical result, recording the time length corresponding to the content tag with the time length being more than or equal to a preset threshold time length as 1, and recording the time length corresponding to the content tag with the time length being less than the threshold time length as 0; aggregating statistical results obtained after the timestamp information is in a preset time period and has the same seat identification and the time length corresponding to the content tags is quantified to obtain the total number of each content tag in the preset time period and the total number of each content tag reaching the standard in the preset time period; and calculating the proportion of each content label in the preset time period and the time standard reaching rate of each content label in the preset time period aiming at each aggregation result.
And quantifying the time length corresponding to each content tag contained in the statistical result, recording the time length corresponding to the content tag with the time length being greater than or equal to a preset threshold time length as 1, and recording the time length corresponding to the content tag with the time length being less than the threshold time length as 0. For example, in a statistical result generated by 5 text data, the number of open white labels is 1, 0, 1, the corresponding duration of the open white labels is 10 seconds, 20 seconds, 0 seconds, 5 seconds, 15 seconds, wherein the first three statistical results (the number of open white labels is 1, 0, the corresponding duration of the open white labels is 10 seconds, 20 seconds, 0 seconds) have the same seat identifier x1, the last two statistical results (the number of open white labels is 1, the corresponding duration of the open white labels is 5 seconds, 15 seconds) have the same seat identifier y1, the timestamp information of the 5 statistical results is 20.1.1, 20.1.2, 20.1.3, 20.1.1, 20.1.2 in sequence, the timestamp information includes month and day information, the preset duration threshold value is 15 seconds, the first timestamp of the open white labels is 0, 1, 0, 1, and 1, respectively, the mark 1 represents that the duration reaches the standard, and the mark 0 represents that the duration does not reach the standard. Aggregating statistical results obtained after the timestamp information is within a preset time period and has the same seat identification and the time length corresponding to the content tags is quantified to obtain the total number of each content tag within the preset time period and the total number of each content tag reaching the standard within the preset time period; as the statistical results generated from the 5 text data as described above, when the preset time period is 20.1.1 to 20.1.2, the aggregated result is: x1 corresponds to the polymerization result: the number of the open field white labels is 2, and the total number of the time lengths corresponding to the open field white labels reaching the standard is 1; y1 corresponds to the polymerization result: the number of the open field white labels is 1, and the total number of the corresponding open field white labels reaching the standard is 1. Calculating the occupation ratio of each content label in the preset time period and the time reaching rate of each content label in the preset time period aiming at each aggregation result, and taking the two aggregation results as an example, calculating the occupation ratio of the open field white label in the time period from 20.1.1 to 20.1.2 in the aggregation results corresponding to x 1: 2/2 is obtained by the open field white label quantity/total item number of the statistical result; duration hit rate of open white tag during the period 20.1.1 to 20.1.2: the total number of the time lengths corresponding to the open field white labels reaching the standard/the total number of the statistical results is 1/2; calculating the proportion of the open field white label in the time period from 20.1.1 to 20.1.2 in the corresponding aggregation result of y 1: 1/2 is obtained by the open field white label quantity/total item number of the statistical result; duration hit rate of open white tag during the period 20.1.1 to 20.1.2: and the total number of the time lengths corresponding to the open field white labels reaching the standard/the total number of the statistical results is 1/2. And counting the total number of each content label, the total number of the time length of each content label reaching the standard, the percentage of each content label and the time length reaching rate of each content label to obtain the quantitative index of the corresponding seat. Taking the two aggregation results and the two calculation results as examples, the quantization indexes of x1 and y1 are obtained, where the quantization indexes of x1 in the time period of 20.1.1 to 20.1.2 are: the number of the open-field white labels is 2, the total number of the time length reaching the standard corresponding to the open-field white labels is 1, the proportion of the open-field white labels is 2/2, and the time length reaching rate of the open-field white labels is 1/2; the quantization index of y1 in the time period 20.1.1 to 20.1.2 is: the number of the open-field white labels is 1, the total number of the time length reaching the standard corresponding to the open-field white labels is 1, the ratio of the open-field white labels is 1/2, and the time length reaching rate of the open-field white labels is 1/2. And respectively obtaining quantitative indexes of x1 and y1 in the period of 20.1.1 to 20.1.2. This example is merely one embodiment of the present application and is not intended to limit the present application.
Alternatively, the aggregation may be performed in time periods of daily, weekly, monthly, quarterly, yearly, etc., based on the time stamp information.
It should be noted that, the process of performing quantization preprocessing on the statistical result to obtain the corresponding quantization index is not limited to the above-described embodiment, and optionally, according to the identifier representing the agent and the timestamp information, the statistical results with the same agent and the timestamp information in the same preset time period are aggregated to obtain the aggregation results of all the agents included in the statistical results, and then the quantization indexes of the corresponding agents in the time period are obtained by calculating the percentage of each content tag and the time standard-reaching rate of each content tag, and the like, and then the aggregation results or the quantization indexes corresponding to all the agents are aggregated according to the team information of the agent included in the identifier representing the agent, and the aggregation results or the quantization indexes with the same team information are obtained to obtain the aggregation results of the team, and the percentage of each content tag, the time of each content tag, and the time of each agent are calculated, And obtaining the quantitative indexes of the corresponding team in the time period according to the data such as the time standard-reaching rate of each content label. This example is merely one embodiment of the present application and is not intended to limit the present application.
S400: executing preset management operation corresponding to the quantization index
After the quantitative index is obtained, executing preset management operation corresponding to the quantitative index, for example, judging whether the daily/weekly open field white standard reaching rate is smaller than a set management threshold, if so, sending a reminding message to an agent, if not, sending a warning message to a captain, and if not, automatically entering KPI (key performance indicator) for the third time. Or, if the introduction service error rate is greater than the set management threshold value, sending reminding information to the corresponding coach, and if the error rate is greater than the threshold value for multiple times, recording the KPI check of the coach. The information of the seats, team leaders, corresponding coaches and the like is obtained by representing the identifiers of the seats.
Please refer to fig. 2, which is a device 100 for intelligently managing agents according to an embodiment of the present disclosure, the device includes an obtaining module 110, a statistics module 120, a processing module 130, and a management module 140.
The obtaining module 110 is configured to obtain text data corresponding to a voice file of an agent, where the text data includes content tags obtained by classifying according to preset management indexes and time information corresponding to each content tag in the voice file.
The counting module 120 is configured to count the number of content tags appearing in the text data and not appearing in the management index, and count a duration corresponding to each content tag in the text data, to obtain a statistical result, where the duration corresponding to each content tag is obtained according to the time information corresponding to the content tag.
The processing module 130 is configured to perform quantization preprocessing on the statistical result to obtain a corresponding quantization index, where the quantization index is used to represent the service capability of the agent.
The management module 140 is configured to perform a preset management operation corresponding to the quantization index.
Optionally, the obtaining module 110 is further configured to obtain a voice file; performing voice recognition on the voice file to obtain initial text data, wherein each sentence in the initial text data corresponds to time information; preprocessing the initial text data to obtain text data; classifying the contents in the data according to preset management indexes to obtain content labels corresponding to classification categories; and for each content tag, determining the time information of each sentence included in the content tag, which corresponds to the content tag in the voice file.
Optionally, the obtaining module 110 is further configured to select text data belonging to an agent from the initial text data; and adding identification representing the agent and timestamp information in the text data belonging to the agent.
Optionally, the obtaining module 110 is further configured to convert the format of the obtained initial voice file into a preset standard format, so as to obtain the voice file.
Optionally, the statistical module 120 is specifically configured to, for each text data, record the number of content tags that do not appear in the management index in the text data as 0, and record the number of content tags that appear in the management index as 1.
Optionally, the processing module 130 is specifically configured to quantize a duration corresponding to each content tag included in the statistical result, and record a duration corresponding to a content tag whose duration is greater than or equal to a preset threshold duration as 1, and record a duration corresponding to a content tag whose duration is less than the threshold duration as 0; aggregating the statistical results which have the same seat identification and quantify the time length corresponding to the content label to obtain the total number of each content label and the total number of each content label with the time length reaching the standard; and calculating the occupation ratio of each content label and the time length standard-reaching rate of each content label aiming at each aggregation result, wherein the total number of each content label, the time length standard-reaching total number of each content label, the occupation ratio of each content label and the time length standard-reaching rate of each content label are quantization indexes corresponding to the seat.
Optionally, the processing module 130 is specifically configured to quantize a duration corresponding to each content tag included in the statistical result, and record a duration corresponding to a content tag whose duration is greater than or equal to a preset threshold duration as 1, and record a duration corresponding to a content tag whose duration is less than the threshold duration as 0; aggregating statistical results obtained after the timestamp information is in a preset time period and has the same seat identification and the time length corresponding to the content tags is quantified to obtain the total number of each content tag in the preset time period and the total number of each content tag reaching the standard in the preset time period; and calculating the occupation ratio of each content label in the preset time period and the time standard-reaching rate of each content label in the preset time period aiming at each aggregation result, wherein the total number of each content label in the preset time period, the total number of each content label in the preset time period for reaching the time standard, the occupation ratio of each content label in the preset time period and the time standard-reaching rate of each content label in the preset time period are corresponding quantitative indexes of the seat in the preset time period.
The functions that the intelligent agent management apparatus 100 needs to implement are described in detail in the foregoing, and will not be described in detail herein.
Please refer to fig. 3, which is a robot according to an embodiment of the present disclosure. The robot 200 includes: a transceiver 210, a memory 220, a communication bus 230, and a processor 240.
The elements of the transceiver 210, the memory 220, and the processor 240 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, the components may be electrically coupled to each other via one or more communication buses 230 or signal lines. The transceiver 210 is used for transceiving data. The memory 220 is used for storing a computer program, such as the apparatus 100 storing the software functional modules shown in fig. 2, i.e., the intelligent management agent. The device 100 for intelligent agent management includes at least one software function module, which may be stored in the memory 220 in the form of software or firmware (firmware) or solidified in an Operating System (OS) of the robot 200. The processor 240 is configured to execute an executable module stored in the memory 220, such as a software function module or a computer program included in the apparatus 100 for intelligent agent management. For example, the processor 240 is configured to obtain text data corresponding to a voice file of an agent, where the text data includes content tags obtained by classifying according to preset management indexes and time information corresponding to each content tag in the voice file; counting the number of content tags appearing in the text data and not appearing in the management index, and counting the duration corresponding to each content tag in the text data to obtain a counting result, wherein the duration corresponding to each content tag is obtained according to the time information corresponding to the content tag; carrying out quantitative preprocessing on the statistical result to obtain a corresponding quantitative index, wherein the quantitative index is used for representing the service capability of the seat; and executing preset management operation corresponding to the quantization index.
The Memory 220 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor 240 may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor 240 may be any conventional processor or the like.
The embodiment of the present application further provides a non-volatile computer-readable storage medium (hereinafter, referred to as a storage medium), where a computer program is stored on the storage medium, and when the computer program is run by the robot 200, the computer program executes the above-mentioned method for intelligently managing the agent.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (10)

1. A method for intelligently managing agents, comprising:
acquiring text data corresponding to a voice file of an agent, wherein the text data comprises content labels obtained by classifying according to preset management indexes and time information corresponding to each content label in the voice file;
counting the number of content tags appearing in the text data and not appearing in the management index, and counting the duration corresponding to each content tag in the text data to obtain a counting result, wherein the duration corresponding to each content tag is obtained according to the time information corresponding to the content tag;
carrying out quantitative preprocessing on the statistical result to obtain a corresponding quantitative index, wherein the quantitative index is used for representing the service capability of the seat;
and executing preset management operation corresponding to the quantization index.
2. The method of claim 1, wherein the text data comprises a plurality of text data, and counting the number of content tags that appear and do not appear in the text data in the management metrics comprises:
for each text data, the number of content tags in the text data that do not appear in the management index is recorded as 0, and the number of content tags that appear in the management index is recorded as 1.
3. The method for intelligently managing agents according to claim 1, wherein the text data includes a plurality of text data, each text data further includes an identifier representing an agent, and the step of performing quantization preprocessing on the statistical result to obtain a corresponding quantization index includes:
quantifying the time length corresponding to each content tag contained in the statistical result, recording the time length corresponding to the content tag with the time length being greater than or equal to a preset threshold time length as 1, and recording the time length corresponding to the content tag with the time length being less than the threshold time length as 0;
aggregating the statistical results which have the same seat identification and quantify the time length corresponding to the content label to obtain the total number of each content label and the total number of each content label with the time length reaching the standard;
and calculating the occupation ratio of each content label and the time length standard-reaching rate of each content label aiming at each aggregation result, wherein the total number of each content label, the time length standard-reaching total number of each content label, the occupation ratio of each content label and the time length standard-reaching rate of each content label are quantitative indexes corresponding to the seat.
4. The method for intelligent agent management according to claim 1, wherein the text data includes a plurality of text data, each text data includes an identifier representing an agent and timestamp information, and the statistical result is subjected to quantization preprocessing to obtain a corresponding quantization index, including:
quantifying the time length corresponding to each content tag contained in the statistical result, recording the time length corresponding to the content tag with the time length being greater than or equal to a preset threshold time length as 1, and recording the time length corresponding to the content tag with the time length being less than the threshold time length as 0;
aggregating statistical results obtained after the timestamp information is within a preset time period and has the same seat identification and the time length corresponding to the content tags is quantified to obtain the total number of each content tag within the preset time period and the total number of each content tag reaching the standard within the preset time period;
and calculating the proportion of each content label in the preset time period and the time standard-reaching rate of each content label in the preset time period aiming at each aggregation result, wherein the total number of each content label in the preset time period, the total number of each content label in the preset time period for reaching the time standard, the proportion of each content label in the preset time period, and the time standard-reaching rate of each content label in the preset time period are corresponding quantitative indexes of the seat in the preset time period.
5. The method of intelligently managing agents of claim 1, wherein prior to obtaining the textual data, the method further comprises:
acquiring a voice file;
performing voice recognition on the voice file to obtain initial text data, wherein each sentence in the initial text data corresponds to time information;
preprocessing the initial text data to obtain text data;
classifying the contents in the data according to preset management indexes to obtain content labels corresponding to classification categories;
and for each content tag, determining the time information corresponding to the content tag in the voice file according to the time information of each statement included in the content tag.
6. The method of intelligently managing agents of claim 5, wherein pre-processing the initial text data comprises:
selecting text data belonging to the seat from the initial text data;
and adding identification representing the agent and timestamp information in the text data belonging to the agent.
7. The method of intelligent agent management according to claim 6, wherein obtaining a voice file comprises:
and converting the format of the obtained initial voice file into a preset standard format to obtain the voice file.
8. An apparatus for intelligently managing agents, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring text data corresponding to a voice file of an agent, and the text data comprises content tags obtained by classifying according to preset management indexes and time information corresponding to each content tag in the voice file;
the statistical module is used for counting the number of the content tags appearing and not appearing in the management index in the text data and counting the duration corresponding to each content tag in the text data to obtain a statistical result, wherein the duration corresponding to each content tag is obtained according to the time information corresponding to the content tag;
the processing module is used for carrying out quantitative preprocessing on the statistical result to obtain a corresponding quantitative index, and the quantitative index is used for representing the service capability of the seat;
and the management module is used for executing preset management operation corresponding to the quantization index.
9. A robot, comprising: a memory and a processor, the memory and the processor connected;
the memory is used for storing programs;
the processor to invoke a program stored in the memory to perform the method of any of claims 1-7.
10. A storage medium having stored thereon a computer program which, when executed by a computer, performs the method of any one of claims 1-7.
CN202011275337.5A 2020-11-13 2020-11-13 Method and device for intelligently managing agents, robot and storage medium Active CN112380381B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011275337.5A CN112380381B (en) 2020-11-13 2020-11-13 Method and device for intelligently managing agents, robot and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011275337.5A CN112380381B (en) 2020-11-13 2020-11-13 Method and device for intelligently managing agents, robot and storage medium

Publications (2)

Publication Number Publication Date
CN112380381A true CN112380381A (en) 2021-02-19
CN112380381B CN112380381B (en) 2024-04-05

Family

ID=74584336

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011275337.5A Active CN112380381B (en) 2020-11-13 2020-11-13 Method and device for intelligently managing agents, robot and storage medium

Country Status (1)

Country Link
CN (1) CN112380381B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975514A (en) * 2016-04-28 2016-09-28 朱宇光 Automatic quality testing method and system
CN109151218A (en) * 2018-08-21 2019-01-04 平安科技（深圳）有限公司 Call voice quality detecting method, device, computer equipment and storage medium
CN109327632A (en) * 2018-11-23 2019-02-12 深圳前海微众银行股份有限公司 Intelligent quality inspection system, method and the computer readable storage medium of customer service recording
CN109933658A (en) * 2019-03-21 2019-06-25 中国联合网络通信集团有限公司 Customer service speaking analysis method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975514A (en) * 2016-04-28 2016-09-28 朱宇光 Automatic quality testing method and system
CN109151218A (en) * 2018-08-21 2019-01-04 平安科技（深圳）有限公司 Call voice quality detecting method, device, computer equipment and storage medium
CN109327632A (en) * 2018-11-23 2019-02-12 深圳前海微众银行股份有限公司 Intelligent quality inspection system, method and the computer readable storage medium of customer service recording
CN109933658A (en) * 2019-03-21 2019-06-25 中国联合网络通信集团有限公司 Customer service speaking analysis method and device

Also Published As

Publication number Publication date
CN112380381B (en) 2024-04-05

Similar Documents

Publication Publication Date Title
CN110020660B (en) Integrity assessment of unstructured processes using Artificial Intelligence (AI) techniques
US10599670B2 (en) Performance estimation system utilizing a data analytics predictive model
US20210224832A1 (en) Method and apparatus for predicting customer purchase intention, electronic device and medium
CN111383101B (en) Post-credit risk monitoring method, post-credit risk monitoring device, post-credit risk monitoring equipment and computer readable storage medium
CN111401777B (en) Enterprise risk assessment method, enterprise risk assessment device, terminal equipment and storage medium
US9547547B2 (en) Systems and/or methods for handling erroneous events in complex event processing (CEP) applications
US20050283337A1 (en) System and method for correlation of time-series data
JP4453687B2 (en) Text mining device, text mining method, and text mining program
US11816741B2 (en) Automatically labeling data using natural language processing
CN110619462A (en) Project quality assessment method based on AI model
CN110083689A (en) Customer service quality determining method and device, readable storage medium storing program for executing
Fritzsch et al. Estimating the relation between digitalization and the market value of insurers
CN112380381A (en) Method and device for intelligently managing seats, robot and storage medium
CN111369348A (en) Post-loan risk monitoring method, device, equipment and computer-readable storage medium
CN113094424B (en) Method and system for identifying chart mode by constructing multi-level index system
CN113791860B (en) Information conversion method, device and storage medium
CN112929502B (en) Voice recognition method and system based on electric power customer service
CN115689334A (en) Efficiency analysis method and system of warehouse management system and computer equipment
CN115906844B (en) Rule template-based information extraction method and system
CN110929144A (en) Business data management method, system and readable storage medium
CN116739646B (en) Method and system for analyzing big data of network transaction
US20210295426A1 (en) System and method for debt management
CN116702789A (en) Semantic analysis method, semantic analysis device, computer equipment and storage medium
CN117726345A (en) Complaint data processing method and device, electronic equipment and storage medium
CN116976909A (en) SLA evaluation visualization method and system based on service work order system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant