CN115828912B - Method and system for intelligently identifying multiple people to complain about worksheets - Google Patents
Method and system for intelligently identifying multiple people to complain about worksheets Download PDFInfo
- Publication number
- CN115828912B CN115828912B CN202211641294.7A CN202211641294A CN115828912B CN 115828912 B CN115828912 B CN 115828912B CN 202211641294 A CN202211641294 A CN 202211641294A CN 115828912 B CN115828912 B CN 115828912B
- Authority
- CN
- China
- Prior art keywords
- complaint
- worksheets
- word
- appeal
- list
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 6
- 230000002596 correlated effect Effects 0.000 description 3
- 230000008094 contradictory effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 1
Classifications
-
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Machine Translation (AREA)
Abstract
The application relates to the technical field of computers, in particular to a method and a system for intelligently identifying a multi-person simultaneous complaint work order, which comprise the following steps: in response to receiving the claim worksheet, identifying topics and responsibility principals for the claim worksheet; recording the complaint work orders into corresponding identical complaint work order lists according to topics and responsibility subjects of the complaint work orders; in response to the addition of a complaint work order in the complaint work order list, checking whether the number of complaint work orders recorded in the complaint work order list exceeds a resolution threshold; if the number of the resort worksheets recorded in the same resort worksheets list does not exceed the solution threshold, continuing to receive the resort worksheets, and identifying topics and responsibility subjects of the resort worksheets; if the number of the complaint worksheets recorded in the co-complaint worksheets list exceeds the resolution threshold, a resolution prompt is generated to prompt a user to construct a solution for all the complaint worksheets in the co-complaint worksheets list. The method and the system can reduce the workload of the personnel marking the related worksheets of the hotline system and improve the accuracy and the normalization.
Description
Technical Field
The application relates to the technical field of computers, in particular to a method and a system for intelligently identifying a multi-person simultaneous complaint work order.
Background
With the continuous development of urban economy and science and technology, hotline service platforms are built and operated in various places, work orders for people to resort to by hotline feedback are increased year by year, and the importance degree of each city on the hotline resort work orders is higher and higher. The hotline appeal worksheets are found out by similar or repeated appeal of the crowd nature of multiple persons to a certain imagination or problem, and the problem of a batch of persons can be solved by solving one problem, so that the management service efficiency and the people satisfaction can be effectively improved.
The current processing mode for most hotline services mainly uses manual order receiving and manual auxiliary association similar worksheets. In the operation of the hot line business system, the hot line system personnel can find similar worksheets of multiple persons who complain with the same manner in the process of accepting the complaint worksheets, disposing the complaint worksheets or revisiting the complaint worksheets, and the hot line system personnel can realize the association clustering of the similar complaint worksheets by manually associating or setting the complaint worksheets as the similar complaint worksheets. After the hot line business system operates, the appeal work order analysis system can carry out association similarity analysis on similar appeal work orders of the association clusters, and the analysis results of the multi-person co-appeal work orders are presented in a reporting mode.
However, the manual association of multiple people with the complaint worksheets can increase the burden of the users of the hot line business system, and the association efficiency is low and omission easily occurs; in addition, different people are not unified with the same complaint understanding standard, and the irregularity of the associated worksheets exists.
The contents of the complaint worksheets can be segmented and clustered at present, so that the complaint worksheets are labeled or classified, and furthermore, hot line service system personnel can assist in associating a plurality of people with the complaint worksheets through association labels or classification conditions, and cannot automatically associate the plurality of people with the complaint specific label worksheets.
In addition, the method can effectively associate multiple complaint worksheets by associating a combing analysis report of similar complaint worksheets, but the method belongs to post association analysis, and cannot achieve pre-association identification in operation and do no fast identification and decision support of the multiple complaint worksheets before treatment.
Therefore, how to automatically and accurately find a plurality of people complaint worksheets or groups complaint worksheets from a large number of hotline complaint worksheets of citizens, and automatically correlate the front positions of the plurality of people complaint worksheets is a technical problem to be solved by the current technicians in the field.
Disclosure of Invention
The application provides a method and a system for intelligently identifying a multi-person co-complaint work order, which are used for accurately finding out the multi-person co-complaint work order or group co-complaint work order and automatically correlating the prepositions of the multi-person co-complaint work orders, thereby greatly reducing the workload of marking the correlated work orders by hot line system personnel and improving the accuracy and the normalization.
In order to solve the technical problems, the application provides the following technical scheme:
a method for intelligently identifying a plurality of people to complain about a work order comprises the following steps: step S110, identifying topics and responsibility subjects of the resort work orders in response to receiving the resort work orders; step S120, recording the demand worksheet into a corresponding same-demand worksheet list according to topics and responsibility subjects of the demand worksheets; step S130, in response to the fact that the complaint worksheets are added in the complaint worksheets list, checking whether the number of the complaint worksheets recorded in the complaint worksheets list exceeds a solution threshold; step S140, if the number of the complaint worksheets recorded in the complaint worksheets list does not exceed the resolution threshold, returning to step S110, continuously receiving the complaint worksheets, and identifying topics and responsibility subjects of the complaint worksheets; and step S150, if the number of the complaint worksheets recorded in the same complaint worksheets list exceeds a resolution threshold, generating a resolution prompt to prompt a user to construct a solution for all the complaint worksheets in the same complaint worksheets list.
The method for intelligently identifying the multi-person co-complaint worksheets as described above, wherein the step S110 preferably comprises the following sub-steps: after receiving the demand work orders, preprocessing the demand work orders to obtain demand text information; extracting words from the appeal text information, and collecting the extracted words together to form a appeal text information word set; extracting keywords from the text message word set of the appeal according to a preset history appeal text message total set; calculating the difference between the keywords and all preset topics and all responsibility subjects, taking the topic with the smallest difference with the keywords as the topic of the appeal work order, and taking the responsibility subject with the smallest difference with the keywords as the responsibility subject of the appeal work order.
The method for intelligently identifying the multi-person co-complaint worksheets as described above, wherein the solution threshold is preferably determined according to the topic property value of the complaint worksheets recorded in the co-complaint worksheets list, the responsibility main property value of the complaint worksheets and the maximum number of complaint worksheets which can be recorded in the co-complaint worksheets list.
In the method for intelligently identifying the multi-person co-complaint worksheets, preferably, a plurality of co-complaint worksheets lists are preset, one co-complaint worksheets list records the complaint worksheets with the same topics and responsibility subjects, and different co-complaint worksheets list records the complaint worksheets with different topics and responsibility subjects.
The method for intelligently identifying the multi-person co-complaint worksheets preferably comprises the following steps of: and removing invalid information and adding missing information.
A system for intelligently identifying a plurality of people complaining work orders, comprising: the device comprises an identification unit, a recording unit, a judging unit, a notification unit and a prompt generating unit; the identification unit is used for identifying topics and responsibility subjects of the resort work orders in response to receiving the resort work orders; the recording unit records the complaint work orders into corresponding identical complaint work order lists according to topics and responsibility subjects of the complaint work orders; the judging unit responds to the fact that the complaint worksheets are added in the complaint worksheets list, and checks whether the number of the complaint worksheets recorded in the complaint worksheets list exceeds a solution threshold; if the number of the resort worksheets recorded in the resort worksheets list does not exceed the solution threshold, the notification unit notifies the identification unit to continuously receive the resort worksheets and identifies topics and responsibility subjects of the resort worksheets; if the number of the complaint worksheets recorded in the co-complaint worksheets list exceeds the solution threshold, the prompt generation unit generates a solution prompt to prompt the user to construct a solution for all the complaint worksheets in the co-complaint worksheets list.
The system for intelligently identifying the multi-person simultaneous complaint worksheets comprises the system for intelligently identifying the multi-person simultaneous complaint worksheets, wherein the system preferably carries out preprocessing on the complaint worksheets after receiving the complaint worksheets to obtain the complaint text information; extracting words from the appeal text information, and collecting the extracted words together to form a appeal text information word set; extracting keywords from the text message word set of the appeal according to a preset history appeal text message total set; calculating the difference between the keywords and all preset topics and all responsibility subjects, taking the topic with the smallest difference with the keywords as the topic of the appeal work order, and taking the responsibility subject with the smallest difference with the keywords as the responsibility subject of the appeal work order.
The system for intelligently identifying the multi-person co-complaint worksheets as described above, wherein the solution threshold is preferably determined according to the topic property value of the complaint worksheets recorded in the co-complaint worksheets list, the responsibility main property value of the complaint worksheets and the maximum number of complaint worksheets which can be recorded in the co-complaint worksheets list.
In the system for intelligently identifying the multi-person co-complaint worksheets, preferably, a plurality of co-complaint worksheets lists are preset, one co-complaint worksheets list records the complaint worksheets with the same topics and responsibility subjects, and different co-complaint worksheets list records the complaint worksheets with different topics and responsibility subjects.
The system for intelligently identifying the multi-person co-complaint worksheets as described above, wherein the preprocessing of the complaint worksheets preferably comprises the following steps: and removing invalid information and adding missing information.
Compared with the background art, the method and the system for intelligently identifying the multi-person co-complaint work orders can accurately find out the multi-person co-complaint work orders or the group co-complaint work orders, and automatically correlate the pre-arranged multi-person co-complaint work orders, so that the workload of marking the correlated work orders by the personnel of the hot line system is greatly reduced, and the accuracy and the normalization are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a flow chart of a method for intelligently identifying a multi-person co-complaint work order provided by an embodiment of the application;
FIG. 2 is a schematic diagram of a system for intelligently identifying a multi-person co-complaint work order according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
Example 1
Referring to fig. 1, fig. 1 is a flowchart of a method for intelligently identifying a plurality of people and complaining worksheets according to an embodiment of the present application.
The application provides a method for intelligently identifying a multi-person simultaneous complaint work order, which comprises the following steps:
step S110, identifying topics and responsibility subjects of the resort work orders in response to receiving the resort work orders;
after receiving the demand worksheet, preprocessing the demand worksheet, for example: invalid information (contradictory information, information against facts, etc.), missing information (the position where information is missing is found, and missing information is added at the position), etc., thereby obtaining the complaint text information a.
Word extraction is carried out on the appeal text information A, and the extracted words are gathered together to form a appeal text information word set A' = { a 1 、a 2 、…、a i 、…、a n}, wherein ,a1 To claim the 1 st word in the text information word set A', a 2 To claim the 2 nd word in the text information word set A', a i To appeal to the ith word, a, in the text information word set A' n To claim the nth word in the text message word set a'.
In addition, a history appeal text information total set w= { W is preset before the appeal work order is received 1 、w 2 、…、w j 、…、w m}, wherein ,w1 For the 1 st text in the total set of historical appeal text information W, W 2 For the 2 nd text in the total set of historical appeal text information W j For the j-th text in the total set of historical appeal text information W, W m The mth text in the total set of historical appeal text information W. Wherein, the preset history appeal text information total set W is set according to all the appeal text information of the history.
And extracting keywords from the complaint text information word set A' according to the historical complaint text information total set W. Specifically, calculating word frequency of each word in the appeal text information word set A' according to the history appeal text information total set W; and extracting words with word frequencies higher than a preset value in the word set A' of the appeal text information as key words.
As an example, according to the formulaCalculating word frequency of each word in the resort text information word set A'; wherein i=1, 2, …, n; j=1, 2, …, m; m is M i To appeal to word a in text information word set A i Word frequency, TA of (A) i To appeal word a in text message word set A i Frequency number appearing in the prosecution text message A, < >>To resort to the sum of the frequency of all words appearing in the text information A, FA i The text information total set W for history appeal contains word a i M is the number of texts in the total set of history-appeal text information W.
Calculating the difference between the keywords and all preset topics and all responsibility subjects, taking the topic with the smallest difference with the keywords as the topic of the appeal work order, and taking the responsibility subject with the smallest difference with the keywords as the responsibility subject of the appeal work order. Specifically, according to the formulaCalculating a keyword x and a preset topic y u Difference between->Wherein x' is the weight value of the keyword x, < ->Is topic y u The weight value of the alpha word of (2), beta is the topic y u Is the number of words; according to formula->Calculating a keyword x and a preset responsibility main body z f Difference between->Wherein x' is the weight value of the keyword x, < ->As responsible subject z f The weight value of the f-th word of (2), theta is the responsibility main body z f Is the number of words of (a).
Step S120, recording the demand worksheet into a corresponding same-demand worksheet list according to topics and responsibility subjects of the demand worksheets;
the method comprises the steps of presetting a plurality of same-complaint worksheets, recording the complaint worksheets with the same topics and responsibility subjects in one same-complaint worksheet list, and recording the complaint worksheets with different topics and responsibility subjects in different same-complaint worksheets. After identifying the topic and responsibility main body of the appeal work order, the appeal work order needs to be recorded into the same appeal work order list corresponding to the topic and responsibility main body.
Step S130, in response to the fact that the complaint worksheets are added in the complaint worksheets list, checking whether the number of the complaint worksheets recorded in the complaint worksheets list exceeds a solution threshold;
the solution threshold may be determined according to topic property values of the resort worksheets, responsibility body property values of the resort worksheets, and experience recorded in the co-resort worksheets list. In addition, the solution threshold may be determined according to the topic property value of the complaint work order recorded in the complaint work order list, the responsibility body property value of the complaint work order, and the maximum number of complaint work orders that can be recorded in the complaint work order list. Specifically, it can be according to the formulaCalculating to obtain a solution threshold T', wherein T is the maximum number of the complaint worksheets which can be recorded by the same complaint worksheets list, and Q is the complaint worksheetsV is the responsibility principal property value of the claim worksheet. And, the formula->May be obtained by analyzing the regularity of the historical data.
Step S140, if the number of the complaint worksheets recorded in the complaint worksheets list does not exceed the resolution threshold, returning to step S110, continuously receiving the complaint worksheets, and identifying topics and responsibility subjects of the complaint worksheets;
if the number of the resort worksheets recorded in the resort worksheets list does not exceed the resolution threshold, it is indicated that the resort worksheets recorded in the resort worksheets list are not urgent and can be processed later, so in this case, the process may return to step S110 to continue receiving the resort worksheets, and identify topics and responsibility subjects of the resort worksheets to accumulate more resort worksheets.
Step S150, if the number of the complaint worksheets recorded in the same complaint worksheets list exceeds a resolution threshold, generating a resolution prompt to prompt a user to construct a solution for all the complaint worksheets in the same complaint worksheets list;
if the number of the complaint worksheets recorded in the co-complaint worksheets list exceeds the resolution threshold, the fact that the complaint worksheets recorded in the co-complaint worksheets list are urgent and must be resolved immediately is indicated, so that in this case, a resolution prompt needs to be generated to prompt a user to construct a solution for all the complaint worksheets in the co-complaint worksheets list so as to resolve all the complaint worksheets in the co-complaint worksheets list according to the solution.
Example two
Referring to fig. 2, fig. 2 is a schematic diagram of a system for intelligently identifying a plurality of people and complaining worksheets according to an embodiment of the present application.
The application provides a system 200 for intelligently identifying a plurality of people to complain about a work order, which comprises: an identification unit 210, a recording unit 220, a judgment unit 230, a notification unit 240, and a hint generation unit 250.
The identifying unit 210 identifies topics and responsibility subjects of the claim worksheet in response to receiving the claim worksheet.
After receiving the demand worksheet, preprocessing the demand worksheet, for example: invalid information (contradictory information, information against facts, etc.), missing information (the position where information is missing is found, and missing information is added at the position), etc., thereby obtaining the complaint text information a.
Word extraction is carried out on the appeal text information A, and the extracted words are gathered together to form a appeal text information word set A' = { a 1 、a 2 、…、a i 、…、a n}, wherein ,a1 To claim the 1 st word in the text information word set A', a 2 To claim the 2 nd word in the text information word set A', a i To appeal to the ith word, a, in the text information word set A' n To claim the nth word in the text message word set a'.
In addition, a history appeal text information total set w= { W is preset before the appeal work order is received 1 、w 2 、…、w j 、…、w m}, wherein ,w1 For the 1 st text in the total set of historical appeal text information W, W 2 For the 2 nd text in the total set of historical appeal text information W j For the j-th text in the total set of historical appeal text information W, W m The mth text in the total set of historical appeal text information W. Wherein, the preset history appeal text information total set W is set according to all the appeal text information of the history.
And extracting keywords from the complaint text information word set A' according to the historical complaint text information total set W. Specifically, calculating word frequency of each word in the appeal text information word set A' according to the history appeal text information total set W; and extracting words with word frequencies higher than a preset value in the word set A' of the appeal text information as key words.
As an example, according to the formulaComputing words that appeal to each word in the text information word set AFrequency; wherein i=1, 2, …, n; j=1, 2, …, m; m is M i To appeal to word a in text information word set A i Word frequency, TA of (A) i To appeal word a in text message word set A i Frequency number appearing in the prosecution text message A, < >>To resort to the sum of the frequency of all words appearing in the text information A, FA i The text information total set W for history appeal contains word a i M is the number of texts in the total set of history-appeal text information W.
Calculating the difference between the keywords and all preset topics and all responsibility subjects, taking the topic with the smallest difference with the keywords as the topic of the appeal work order, and taking the responsibility subject with the smallest difference with the keywords as the responsibility subject of the appeal work order. Specifically, according to the formulaCalculating a keyword x and a preset topic y u Difference between->Wherein x' is the weight value of the keyword x, < ->Is topic y u The weight value of the alpha word of (2), beta is the topic y u Is the number of words; according to formula->Calculating a keyword x and a preset responsibility main body z f Difference between->Wherein x' is the weight value of the keyword x, < ->As responsible subject z f The weight value of the f-th word of (2), theta is the responsibility main body z f Is the number of words of (a).
The recording unit 220 records the complaint worksheet to the corresponding co-complaint worksheet list according to the topics and the responsibility subjects of the complaint worksheets.
The method comprises the steps of presetting a plurality of same-complaint worksheets, recording the complaint worksheets with the same topics and responsibility subjects in one same-complaint worksheet list, and recording the complaint worksheets with different topics and responsibility subjects in different same-complaint worksheets. After identifying the topic and responsibility main body of the appeal work order, the appeal work order needs to be recorded into the same appeal work order list corresponding to the topic and responsibility main body.
In response to the addition of the complaint worksheets in the complaint worksheet list, the determination unit 230 checks whether the number of complaint worksheets recorded in the complaint worksheet list exceeds the resolution threshold.
The solution threshold may be determined according to topic property values of the resort worksheets, responsibility body property values of the resort worksheets, and experience recorded in the co-resort worksheets list. The solution threshold may also be determined according to the topic property value of the complaint work order recorded in the complaint work order list, the responsibility body property value of the complaint work order, and the maximum number of complaint work orders that can be recorded in the complaint work order list. Specifically, it can be according to the formulaAnd calculating to obtain a solution threshold T', wherein T is the maximum number of the resort worksheets which can be recorded by the same resort worksheets list, Q is the topic property value of the resort worksheets, and V is the responsibility main body property value of the resort worksheets. And, the formula->May be obtained by analyzing the regularity of the historical data.
If the number of the complaint worksheets recorded in the same complaint worksheets list does not exceed the resolution threshold, the notification unit 240 notifies the recognition unit 210 to continue receiving the complaint worksheets and recognizes topics and responsibility subjects of the complaint worksheets.
If the number of the resort worksheets recorded in the resort worksheets list does not exceed the resolution threshold, the resort worksheets recorded in the resort worksheets list are not urgent and can be processed later, so that in this case, the resort worksheets can be continuously received, topics and responsibility subjects of the resort worksheets can be identified, and more resort worksheets can be accumulated.
If the number of complaint worksheets recorded in the co-complaint worksheets list exceeds the resolution threshold, the prompt generation unit 250 generates a resolution prompt to prompt the user to construct a solution for all the complaint worksheets in the co-complaint worksheets list.
If the number of the complaint worksheets recorded in the co-complaint worksheets list exceeds the resolution threshold, the fact that the complaint worksheets recorded in the co-complaint worksheets list are urgent and must be resolved immediately is indicated, so that in this case, a resolution prompt needs to be generated to prompt a user to construct a solution for all the complaint worksheets in the co-complaint worksheets list so as to resolve all the complaint worksheets in the co-complaint worksheets list according to the solution.
According to the method and the system for intelligently identifying the multi-person co-complaint worksheets, topics and responsibility bodies of the complaint worksheets can be intelligently analyzed in the acceptance stage of the complaint worksheets, so that the multi-person co-complaint worksheets or group co-complaint worksheets can be accurately found, and the multi-person co-complaint worksheets are recorded in the co-complaint worksheets list so as to correlate the multi-person co-complaint worksheets, thereby greatly reducing the workload of marking the correlated worksheets by hot line system staff and improving the accuracy and standardization.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (8)
1. The method for intelligently identifying the multi-person co-complaint worksheets is characterized by comprising the following steps of:
step S110, identifying topics and responsibility subjects of the resort work orders in response to receiving the resort work orders;
step S110 includes the following sub-steps:
after receiving the demand work orders, preprocessing the demand work orders to obtain demand text information;
extracting words from the appeal text information, and collecting the extracted words together to form a appeal text information word set;
calculating word frequency of each word in the appeal text information word set according to the history appeal text information total set, and extracting words with word frequency higher than a preset value in the appeal text information word set as key words;
according to the formulaComputing the complaint text message word set +.>Word frequency of each word in (a); wherein (1)> ；/>To appeal to text message word set +.>Word +.>Word frequency of->To appeal to text message word set +.>Chinese word->Appears in the complaint text message->Frequency of->To appeal text information->The sum of the frequency of all words occurring in +.>For the total set of historical appeal text messages +.>The word->Text number of->For the total set of historical appeal text messages +.>Wen Benshu in (a);
calculating the difference between the keywords and all preset topics and all responsibility subjects, taking the topic with the smallest difference with the keywords as the topic of the appeal work order, and taking the responsibility subject with the smallest difference with the keywords as the responsibility subject of the appeal work order;
according to the formulaCalculating keywords +.>Is->Difference between->, wherein ,is keyword->Weight value of->Is the topic->Is>Weight value of individual word +_>Is the topic->Is the number of words; according to formula->Calculating keywords +.>Is in charge of the preset responsibility subject->Difference between->, wherein ,/>Is keyword->Weight value of->Is responsible for->Is>Weight value of individual word +_>Is responsible for->Is the number of words;
step S120, recording the demand worksheet into a corresponding same-demand worksheet list according to topics and responsibility subjects of the demand worksheets;
step S130, in response to the fact that the complaint worksheets are added in the complaint worksheets list, checking whether the number of the complaint worksheets recorded in the complaint worksheets list exceeds a solution threshold;
step S140, if the number of the complaint worksheets recorded in the complaint worksheets list does not exceed the resolution threshold, returning to step S110, continuously receiving the complaint worksheets, and identifying topics and responsibility subjects of the complaint worksheets;
and step S150, if the number of the complaint worksheets recorded in the same complaint worksheets list exceeds a resolution threshold, generating a resolution prompt to prompt a user to construct a solution for all the complaint worksheets in the same complaint worksheets list.
2. The method for intelligently identifying a multi-person co-complaint work order according to claim 1, wherein the resolution threshold is determined according to a topic property value of the complaint work order recorded in the co-complaint work order list, a responsibility body property value of the complaint work order, and the maximum number of complaint work orders that can be recorded in the co-complaint work order list.
3. The method for intelligently identifying multiple simultaneous complaint worksheets according to claim 1, wherein a plurality of simultaneous complaint worksheets are preset, one simultaneous complaint worksheets having the same topic and responsibility are recorded in one simultaneous complaint worksheet list, and the different simultaneous complaint worksheets having different topics and responsibility are recorded in different simultaneous complaint worksheets.
4. The method for intelligently identifying a multi-person co-complaint work order according to claim 1, wherein preprocessing the complaint work order comprises: and removing invalid information and adding missing information.
5. A system for intelligently identifying a plurality of people who complain about a work order, comprising: the device comprises an identification unit, a recording unit, a judging unit, a notification unit and a prompt generating unit;
the identification unit is used for identifying topics and responsibility subjects of the resort work orders in response to receiving the resort work orders;
after receiving the demand work orders, preprocessing the demand work orders to obtain demand text information;
extracting words from the appeal text information, and collecting the extracted words together to form a appeal text information word set;
calculating word frequency of each word in the appeal text information word set according to the history appeal text information total set, and extracting words with word frequency higher than a preset value in the appeal text information word set as key words;
according to the formulaComputing the complaint text message word set +.>Word frequency of each word in (a); wherein, ；/>to appeal to text message word set +.>Word +.>Word frequency of->To appeal to text message word set +.>Chinese word->Appears in the complaint text message->Frequency of->To appeal text information->The sum of the frequency of all words occurring in +.>For the total set of historical appeal text messages +.>The word->Text number of->For the total set of historical appeal text messages +.>Wen Benshu in (a);
calculating the difference between the keywords and all preset topics and all responsibility subjects, taking the topic with the smallest difference with the keywords as the topic of the appeal work order, and taking the responsibility subject with the smallest difference with the keywords as the responsibility subject of the appeal work order;
according to the formulaCalculating keywords +.>Is->Difference between->, wherein ,/>Is keyword->Weight value of->Is the topic->Is>Weight value of individual word +_>Is the topic->Is the number of words; according to formula->Calculating keywords +.>Is in charge of the preset responsibility subject->Difference between->, wherein ,/>Is keyword->Weight value of->Is responsible for->Is>Weight value of individual word +_>Is responsible for->Is the number of words;
the recording unit records the complaint work orders into corresponding identical complaint work order lists according to topics and responsibility subjects of the complaint work orders;
the judging unit responds to the fact that the complaint worksheets are added in the complaint worksheets list, and checks whether the number of the complaint worksheets recorded in the complaint worksheets list exceeds a solution threshold;
if the number of the resort worksheets recorded in the resort worksheets list does not exceed the solution threshold, the notification unit notifies the identification unit to continuously receive the resort worksheets and identifies topics and responsibility subjects of the resort worksheets;
if the number of the complaint worksheets recorded in the co-complaint worksheets list exceeds the solution threshold, the prompt generation unit generates a solution prompt to prompt the user to construct a solution for all the complaint worksheets in the co-complaint worksheets list.
6. The system for intelligently identifying multiple co-complaint worksheets according to claim 5, wherein the resolution threshold is determined according to the topic property value of the complaint worksheets recorded in the co-complaint worksheets list, the responsibility body property value of the complaint worksheets, and the maximum number of complaint worksheets that the co-complaint worksheets list can record.
7. The system for intelligently identifying multiple simultaneous complaint worksheets according to claim 5, wherein a plurality of simultaneous complaint worksheets lists are preset, one simultaneous complaint worksheets list records the complaint worksheets with the same topic and responsibility body, and different simultaneous complaint worksheets list records the complaint worksheets with different topics and responsibility bodies.
8. The system for intelligently identifying multiple simultaneous complaints workflows of claim 5, wherein preprocessing the complaint workflows comprises: and removing invalid information and adding missing information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211641294.7A CN115828912B (en) | 2022-12-20 | 2022-12-20 | Method and system for intelligently identifying multiple people to complain about worksheets |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211641294.7A CN115828912B (en) | 2022-12-20 | 2022-12-20 | Method and system for intelligently identifying multiple people to complain about worksheets |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115828912A CN115828912A (en) | 2023-03-21 |
| CN115828912B true CN115828912B (en) | 2023-08-29 |
Family
ID=85516969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211641294.7A Active CN115828912B (en) | 2022-12-20 | 2022-12-20 | Method and system for intelligently identifying multiple people to complain about worksheets |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115828912B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102957544A (en) * | 2011-08-17 | 2013-03-06 | 中国移动通信集团上海有限公司 | Method and device for transmitting service work orders and service work order processing system |
| CN108875049A (en) * | 2018-06-27 | 2018-11-23 | 中国建设银行股份有限公司 | text clustering method and device |
| CN111222896A (en) * | 2020-01-17 | 2020-06-02 | 中信百信银行股份有限公司 | Customer complaint problem processing method, apparatus, device and storage medium |
| CN112183051A (en) * | 2020-09-02 | 2021-01-05 | 北京源和汇升科技中心(有限合伙) | Intelligent voice follow-up method, system, computer equipment, storage medium and program product |
| CN112487824A (en) * | 2020-11-19 | 2021-03-12 | 平安科技（深圳）有限公司 | Customer service speech emotion recognition method, device, equipment and storage medium |
| CN112732918A (en) * | 2021-01-13 | 2021-04-30 | 国网山东省电力公司日照供电公司 | Complaint work order intelligent classification system |
| CN114065752A (en) * | 2021-10-20 | 2022-02-18 | 北京淇瑀信息科技有限公司 | Text-based risk equipment identification method and device and electronic equipment |
| CN114841146A (en) * | 2022-05-11 | 2022-08-02 | 平安科技（深圳）有限公司 | Text abstract generation method and device, electronic equipment and storage medium |
-
2022
- 2022-12-20 CN CN202211641294.7A patent/CN115828912B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102957544A (en) * | 2011-08-17 | 2013-03-06 | 中国移动通信集团上海有限公司 | Method and device for transmitting service work orders and service work order processing system |
| CN108875049A (en) * | 2018-06-27 | 2018-11-23 | 中国建设银行股份有限公司 | text clustering method and device |
| CN111222896A (en) * | 2020-01-17 | 2020-06-02 | 中信百信银行股份有限公司 | Customer complaint problem processing method, apparatus, device and storage medium |
| CN112183051A (en) * | 2020-09-02 | 2021-01-05 | 北京源和汇升科技中心(有限合伙) | Intelligent voice follow-up method, system, computer equipment, storage medium and program product |
| CN112487824A (en) * | 2020-11-19 | 2021-03-12 | 平安科技（深圳）有限公司 | Customer service speech emotion recognition method, device, equipment and storage medium |
| CN112732918A (en) * | 2021-01-13 | 2021-04-30 | 国网山东省电力公司日照供电公司 | Complaint work order intelligent classification system |
| CN114065752A (en) * | 2021-10-20 | 2022-02-18 | 北京淇瑀信息科技有限公司 | Text-based risk equipment identification method and device and electronic equipment |
| CN114841146A (en) * | 2022-05-11 | 2022-08-02 | 平安科技（深圳）有限公司 | Text abstract generation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115828912A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109189901B (en) | Method for automatically discovering new classification and corresponding corpus in intelligent customer service system | |
| Coussement et al. | Improving customer complaint management by automatic email classification using linguistic style features as predictors | |
| CN109783639B (en) | Mediated case intelligent dispatching method and system based on feature extraction | |
| US7912714B2 (en) | Method for segmenting communication transcripts using unsupervised and semi-supervised techniques | |
| US20170235820A1 (en) | System and engine for seeded clustering of news events | |
| CN108776671A (en) | A kind of network public sentiment monitoring system and method | |
| WO2013068854A2 (en) | Systems, methods, and interfaces for analyzing conceptually-related portions of text | |
| CN110866110A (en) | Conference summary generation method, device, equipment and medium based on artificial intelligence | |
| CN112101971B (en) | Sensitive client identification method, system and storage medium | |
| CN111680073A (en) | Financial service platform policy information recommendation method based on user data | |
| CN116384889A (en) | Intelligent analysis method for information big data based on natural language processing technology | |
| Yang et al. | Understanding online consumer review opinions with sentiment analysis using machine learning | |
| CN111104483A (en) | ICT system fault analysis and auxiliary discrimination method based on machine learning | |
| CN114722191A (en) | Automatic call clustering method and system based on semantic understanding processing | |
| CN112541351B (en) | Method and system for dispatching government service heat line work orders in living construction field | |
| CN115828912B (en) | Method and system for intelligently identifying multiple people to complain about worksheets | |
| CN112488736A (en) | Method and system for analyzing government affair hotline work order data in field of residential construction | |
| Li et al. | Opinion mining of camera reviews based on Semantic Role Labeling | |
| CN111241288A (en) | Emergency sensing system of large centralized power customer service center and construction method | |
| Chen et al. | Adapting the influences of publishers to perform news event detection | |
| CN113538011B (en) | Method for associating non-booked contact information with booked user in electric power system | |
| CN115423361A (en) | Data processing method and device for risk view, storage medium and equipment | |
| CN114862006A (en) | Social work service scheme automatic generation method and device based on artificial intelligence | |
| Li et al. | Text mining strategy of power customer service work order based on natural language processing technology | |
| CN113378916A (en) | Smart archive hierarchical service mode based on cluster analysis |
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 |