CN115641090B - Item distribution method, system, computer device and medium - Google Patents
Item distribution method, system, computer device and medium Download PDFInfo
- Publication number
- CN115641090B CN115641090B CN202211382886.1A CN202211382886A CN115641090B CN 115641090 B CN115641090 B CN 115641090B CN 202211382886 A CN202211382886 A CN 202211382886A CN 115641090 B CN115641090 B CN 115641090B
- Authority
- CN
- China
- Prior art keywords
- processing
- department
- characters
- execution
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 191
- 238000012549 training Methods 0.000 claims description 46
- 238000013145 classification model Methods 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 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
- Machine Translation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, a computer device and a medium for distributing matters, which automatically identify an execution department for execution according to the matching condition of a processing work order and the execution department contained in the processing matters after the corresponding processing matters are matched according to reported information, and realize the automatic matching of the execution department according to the identification characters after the corresponding execution department is re-matched according to the identification characters by splitting the semantic identification of the reported information into the identification characters when the processing work order is not bound with the execution department, thereby preventing the problem that the corresponding execution department cannot be accurately matched due to unclear authority division of the department, solving the problems that the processing work order contained in the processing matters is more and the communication cooperative efficiency is low between the execution departments easily when the authority division of the execution department involved in the processing work order is not clear in the prior art, and improving the processing efficiency of the processing matters.
Description
Technical Field
The present invention relates to item distribution, and more particularly, to an item distribution method, system, computer device, and medium.
Background
In social management, the urban operation command center is responsible for receiving events of different types from different channels and uniformly distributing the events to each treatment department for treatment in a form of a work order;
however, in some processing matters requiring simultaneous collaboration of multiple departments, the processing worksheets included in the processing matters are often more, and when the authority division of the executing departments involved in the processing worksheets is not clear enough, mutual withholding among the departments is easily caused, so that problems of reduced collaboration degree and low collaboration efficiency of communication occur, event promotion is difficult, and the processing efficiency of the processing matters is affected.
Disclosure of Invention
In view of the above, there is a need for a method, a system, a computer device, and a medium for distributing items that can accurately distribute a processing work order according to the division responsibilities corresponding to each receiving department.
The invention provides a transaction distribution method, which specifically comprises the following steps:
reporting information uploaded by a reporting department;
according to the corresponding processing matters matched with the reported information, the processing matters comprise a plurality of processing work orders;
judging whether each processing work order is not matched with a corresponding execution department;
if yes, carrying out semantic splitting on the reported information, so as to split the reported information into adverb characters and main word characters, wherein the adverb characters are adverbs contained in the reported information, and the main word characters are other characters except the adverb characters in the reported information;
and marking the main word characters as identification characters, and matching the execution departments of the processing worksheets according to the identification characters.
Further, the step of matching the execution departments of the processing worksheets according to the identification characters specifically includes:
after each processing work order is switched to a state to be allocated, a first preset word stock matched with the execution department is obtained;
judging whether the number of matches between the identification characters and the first preset word stock exceeds a preset threshold matched with the execution department,
if yes, binding the processing worksheet with the executive department, and determining that the processing worksheet is to be executed by the executive department with successful binding.
Further, the step of matching the execution departments of the processing worksheets according to the identification characters further comprises:
acquiring history treatment data of the processing work order, wherein the history treatment data comprises history report information matched with the processing work order, a history source and a history execution department;
training a preset classification model according to the historical treatment data so as to generate a final matching model, inputting the identification characters into the final matching model for calculation, and outputting a final execution department;
binding the final execution department with the processing worksheet matched with the identification character, thereby determining that the processing worksheet is to be executed by the final execution department.
Further, the step of training a preset classification model according to the historical treatment data to generate a final matching model specifically includes:
storing the history report information, the history source and the history execution department in a preset training table to serve as a training basis of the preset classification model;
acquiring a preset industry word segmentation dictionary as a model word segmentation basis, wherein the preset industry word segmentation dictionary comprises a plurality of industry classification nouns;
circularly matching the history report information, the history source, the history execution department and the preset industry word segmentation dictionary according to a preset matching mode, and integrating successfully matched characters into a training character set;
and after the characters contained in the training character set are subjected to standardized processing and marked as a model training set, inputting the model training set into the preset classification model for training, so as to generate a final matching model.
Further, the step of inputting the identification character into the final matching model for calculation and outputting the final execution department specifically includes:
inputting the identification characters into the final matching model for prediction reduction, so as to output a prediction parameter set;
inputting the prediction parameter set into the final matching model again to perform prediction, so as to output final matching characteristics, wherein the final matching characteristics are contained in the identification characters;
and matching the corresponding executive departments according to the final matching characteristics.
Further, after the step of determining whether each processing worksheet does not match the corresponding execution department, the method further includes:
if not, judging whether part of the processing worksheets are not matched with the corresponding executive departments;
if yes, after each processing work order is switched to a state to be allocated, an execution department successfully matched with the processing work order is acquired and is recorded as a department to be pushed;
acquiring a second preset word stock matched with the department to be pushed;
judging whether the number of matches between the identification characters and the second preset word stock exceeds a preset threshold matched with the execution department,
if yes, binding the processing worksheet with the department to be pushed, and therefore determining that the processing worksheet is executed by the department to be pushed, wherein the department to be pushed is successfully bound.
Further, after the step of determining whether each processing worksheet does not match the corresponding execution department, the method further includes:
if not, judging whether each processing work order is matched with only one execution department;
if yes, binding the processing worksheet with the executive department, and determining that the processing worksheet is to be executed by the executive department with successful binding.
The invention also provides a transaction distribution system, which specifically comprises:
the acquisition unit is used for reporting information uploaded by the reporting department;
the matching unit is used for matching corresponding processing matters according to the reported information, wherein the processing matters comprise a plurality of processing worksheets;
the judging unit is used for judging whether each processing work order is not matched with the corresponding execution department;
the splitting unit is used for judging whether the reported information is the same or not, and carrying out semantic splitting on the reported information so as to generate a plurality of identification characters;
and the binding unit is used for matching the execution departments of the processing worksheets according to the identification characters.
A computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
reporting information uploaded by a reporting department;
according to the corresponding processing matters matched with the reported information, the processing matters comprise a plurality of processing work orders;
judging whether each processing work order is not matched with a corresponding execution department;
if yes, carrying out semantic splitting on the reported information so as to generate a plurality of identification characters;
and matching the executive departments of the processing worksheets according to the identification characters.
A computer readable medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
reporting information uploaded by a reporting department;
according to the corresponding processing matters matched with the reported information, the processing matters comprise a plurality of processing work orders;
judging whether each processing work order is not matched with a corresponding execution department;
if yes, carrying out semantic splitting on the reported information so as to generate a plurality of identification characters;
and matching the executive departments of the processing worksheets according to the identification characters.
According to the item distribution method, system, computer equipment and medium, after corresponding processing items are matched according to the reported information, the execution departments for execution are automatically identified according to the matching condition of the processing worksheets and the execution departments contained in the processing items, when the processing worksheets are not bound with the execution departments, the corresponding execution departments are re-matched according to the identification characters after the reported information is split into identification characters through semantic identification, so that the automatic matching of the execution departments is realized, the problem that the corresponding execution departments cannot be accurately matched due to unclear authority division of the departments is solved, the problems that in the prior art, the processing worksheets contained in the processing items are more, and when the authority division of the execution departments involved in the processing worksheets is not clear enough, communication and cooperative efficiency is low easily caused among the execution departments are solved, and the processing efficiency of the processing items is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Wherein:
FIG. 1 is a method flow diagram of a transaction distribution method in one embodiment;
FIG. 2 is a schematic diagram of a transaction distribution system according to an embodiment;
fig. 3 is a block diagram of a computer device in one embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a transaction distribution method, which specifically includes:
s1, reporting information uploaded by a reporting department;
as described in the step S1, the background system acquires the report information sent by the report department, and it can be understood that the report information is an upper department that can send out a work order task, and the background system refreshes the report information sent by the upper department in real time, so that the operator included in the background system can check the report information, and in addition, the report information includes voice information such as voice call recording and character information such as short message and fax information;
in addition, the background system is generally a background server, and in addition, the background system may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content Delivery Networks (CDNs), basic cloud computing services such as big data and artificial intelligence platforms, and the invention is not limited thereto.
S2, according to the corresponding processing matters matched with the reported information, the processing matters comprise a plurality of processing worksheets;
as described in the above step S2, the background system can understand that the processing item is essentially a processing item process according to the corresponding processing item matched with the reported information, and the background system pre-stores various processing items of different types, and the processing items include a plurality of processing worksheets that need the rest departments to process synchronously or in a set order
S3, judging whether each processing work order is not matched with a corresponding execution department;
as described in the above step S3, the backend system determines whether the corresponding execution units are bound to the processing worksheets included in the processing matters, when each processing worksheet included in the processing matters is bound to a unique corresponding execution unit, the backend system determines that no disorder of responsibility division exists between the execution units, otherwise, when the backend system determines that each processing worksheet included in the processing matters is not bound to an execution unit or is bound to a plurality of execution units, the backend system determines that disorder of responsibility division easily exists between the execution units, and executes step S4;
s4, if yes, carrying out semantic splitting on the reported information so as to generate a plurality of identification characters;
as described in step S4, when the background system determines that each processing work order included in the processing item is not bound to an execution department or is bound to a plurality of execution departments, the background system may identify the reported information by using the semantic identification system, so as to split the reported information into a plurality of identification characters;
for example, the background system may use preset semantic recognition technologies such as ASR and NLP to perform semantic splitting on the report information, so as to split the report information into an adverb character AD and a main word character NN, and it may be understood that the adverb character AD is an adverb contained in the character information, and all the characters in the character information except for the adverb character AD are main word characters NN, and then the background system marks the main word characters NN as recognition characters.
S5, matching the execution departments of the processing worksheets according to the identification characters.
As described in step S5, the execution department of the background system matching each processing work order according to the recognition characters generated by the semantic recognition specifically includes: the execution department binds a plurality of matched characters in advance, when the matched characters are matched with the identification characters, the background system judges that the identification characters are matched with the execution department, and similarly, a processing work order containing the identification characters is matched with the execution department, and the execution department must process the processing work order at the moment, so that the problem that event advancing is too slow due to confusion of responsibility division among the execution departments is prevented;
it can be understood that in this embodiment, the allocation personnel corresponding to the background system may set the execution department corresponding to the direct binding according to the execution department matched with the processing worksheet, or may manually allocate the execution department by using the successfully matched execution department as a reference basis.
According to the method, after the corresponding processing matters are matched according to the reported information, the execution department for execution is automatically identified according to the matching condition of the processing worksheets and the execution departments contained in the processing matters, and when the processing worksheets are not bound with the execution departments, the corresponding execution departments are re-matched according to the identification characters after the semantic identification is split into the identification characters by using the reported information, so that the automatic matching of the execution departments is realized, the problem that the corresponding execution departments cannot be accurately matched due to unclear authority division of the departments is solved, the problems that the processing worksheets contained in the processing matters are more in the prior art, and when the authority division of the execution departments involved in the processing worksheets is not clear enough, the communication cooperative efficiency is easy to occur among the execution departments are solved, and the processing efficiency of the processing matters is improved.
In one embodiment, the step S5 specifically includes:
s51, after each processing work order is switched to a state to be allocated, a first preset word stock matched with the execution department is obtained, whether the number of matches between the identification characters and the first preset word stock exceeds a preset threshold matched with the execution department is judged, if yes, the processing work order is bound with the execution department, and therefore the processing work order is determined to be executed by the execution department which is successfully bound.
As described in the above embodiment, the background system switches all the processing worksheets included in the processing items to the to-be-assigned state, and then the background system obtains the first preset word stock matched with all the execution departments, which can be understood that the first preset word stock is a keyword stock matched with the execution departments, and then the background system determines whether the number of matches of the phrases between the recognition characters and the keyword stock exceeds the preset threshold matched with the execution departments, which can be understood that the preset threshold can be set by the user, and when the number of matches of the phrases between the recognition characters and the keyword stock exceeds the preset threshold, the background system binds the processing worksheets corresponding to the recognition characters with the execution departments corresponding to the keyword stock, so as to determine that the processing worksheets will be executed by the execution departments that are successfully bound.
In one embodiment, the step S5 further includes:
s52, acquiring history treatment data of the processing work order, wherein the history treatment data comprises history report information, history sources and history execution departments matched with the processing work order, training a preset classification model according to the history treatment data so as to generate a final matching model, inputting the identification characters into the final matching model for calculation, outputting a final execution department, binding the final execution department with the processing work order matched with the identification characters, and determining that the processing work order is to be executed by the final execution department.
As described in the above embodiment, the background system acquires the history handling data of the processing work order, and it is understood that the history handling data is history distribution data of the processing work order, including history report information, history source, and history execution department, where the history report information, the history source, and the history execution department are report information corresponding to the processing work order in the history data, report source, and execution department, respectively, and then the background system acquires a preset classification model, inputs the history handling data into the preset classification model to perform model training, thereby forming a final matching model, and finally the background system inputs identification characters corresponding to the processing work order into the final matching model to calculate, and outputs the final execution department, and it is understood that after outputting the final execution department, the background system binds the processing work order matched with the identification characters by the final execution department, thereby determining that the processing work order is to be executed by the final execution department.
In an embodiment, the step of training a preset classification model according to the historical treatment data to generate a final matching model specifically includes:
s53, storing the historical report information, the historical source and the historical execution department in a preset training table as a training basis of the preset classification model, acquiring a preset industry word segmentation dictionary as a model word segmentation basis, wherein the preset industry word segmentation dictionary comprises a plurality of industry classification nouns, carrying out cyclic matching on the historical report information, the historical source and the historical execution department and the preset industry word segmentation dictionary according to a preset matching mode, integrating successfully matched characters into a training character set, carrying out standardized processing on the characters contained in the training character set, and then recording the standardized processing on the characters as a model training set, and inputting the model training set into the preset classification model for training so as to generate a final matching model.
As described in the foregoing embodiment, the background system acquires a preset training table, and it may be understood that the preset training table is used to input data contained in the preset training table into a preset classification model for training, then the background system stores the history report information, the history source and the history execution department in the preset training table as training bases of the preset classification model, then the preset industry word dictionary is used as model word bases, and it may be understood that the preset industry word dictionary includes a plurality of industry classification nouns, and the industry classification nouns are collected by a user and added into the preset industry word dictionary, then the background system performs cycle matching on the history report information, the history source and the history execution department contained in the preset training table with the preset industry word dictionary according to a preset matching mode, during the matching process, characters successfully matched by the background system are integrated into a training character set, and the characters failed to be manually adjusted and then re-matched, thereby implementing repeated training on the preset classification model, and generating a final matching model.
In one embodiment, the step of inputting the identification character into the final matching model for calculation and outputting to a final execution department specifically includes:
s53, inputting the identification characters into the final matching model for prediction reduction, so as to output a prediction parameter set, inputting the prediction parameter set into the final matching model again for prediction, so as to output final matching features, wherein the final matching features are contained in the identification characters, and matching the corresponding execution departments according to the final matching features.
As described in the above embodiment, the background system inputs the identification characters into the final matching model to perform prediction and restoration, and outputs the prediction parameter set generated by the first restoration, and then the background system inputs the prediction parameter set into the final matching model again to perform prediction, so as to output final matching features.
In an embodiment, after the step S3, the method further includes:
s31, if not, judging whether a part of the processing worksheets are not matched with the corresponding executing departments, if so, switching each processing worksheet into a to-be-allocated state, acquiring the executing departments successfully matched with the processing worksheets, marking the to-be-pushed departments, acquiring a second preset word stock matched with the to-be-pushed departments, judging whether the number of the matched identification characters and the second preset word stock exceeds a preset threshold matched with the executing departments, and if so, binding the processing worksheets with the to-be-pushed departments, thereby determining that the processing worksheets are to be executed by the to-be-pushed departments successfully bound.
As described in the above embodiment, when the background system determines that whether each processing work order included in the processing matters has a part of work orders bound to an execution department, and meanwhile, if the part of work orders are not bound to an execution department, then the background system determines that there is a risk of occurrence of a disorder situation in responsibility division before each execution department at this time, then the background system switches each processing work order to a to-be-allocated state, then marks the execution department bound to the processing work order as a to-be-pushed department, and then the background system acquires a second preset word library matched with the to-be-pushed department, where it can be understood that the second preset word library is a keyword library matched with the to-be-pushed department, and then the background system determines whether the number of matches of phrases between an identification character and the keyword library exceeds a preset threshold matched with the to-be-pushed department, where it can be self-set by a user, and when the number of matches between the identification character and the keyword library exceeds the preset threshold, the background system binds the processing work order corresponding to the identification character and the to-be-pushed department, thereby successfully carries out the to-be-pushed by the keyword library;
it can be understood that in this embodiment, the allocation personnel corresponding to the background system may set the execution department corresponding to the direct binding of the to-be-pushed department matched with the processing work order, or may manually allocate the execution department by using the to-be-pushed department successfully matched as a reference basis.
In an embodiment, after the step S3, the method further includes:
s32, if not, judging whether each processing work order is matched with only one execution department, if so, binding the processing work order with the execution department, and further determining that the processing work order is executed by the execution department successfully bound.
As described in the above embodiment, when the background system determines that each processing work order included in the processing matters is bound to a single execution department, the background system determines that the problem of confusion of responsibility division does not exist before each execution department at this time, and the background system binds the processing work order and the execution department singly matched with the processing work order, thereby determining that the processing work order is to be executed by the execution department successfully bound;
it can be understood that in this embodiment, the allocation personnel corresponding to the background system may set the execution department corresponding to the direct binding according to the execution department matched with the processing worksheet, or may manually allocate the execution department by using the successfully matched execution department as a reference basis.
Referring to fig. 2, the present invention further provides a transaction distribution system, which specifically includes:
the acquisition unit 1 is used for reporting information uploaded by a reporting department;
the matching unit 2 is used for matching corresponding processing matters according to the reported information, wherein the processing matters comprise a plurality of processing worksheets;
a judging unit 3, configured to judge whether each of the processing worksheets does not match a corresponding execution department;
the splitting unit 4 is used for judging whether the reported information is the same or not, and performing semantic splitting on the reported information so as to generate a plurality of identification characters;
a binding unit 5 for matching the execution departments of the respective processing worksheets according to the identification characters.
The units are not described here one by one for executing the transaction distribution system.
FIG. 3 illustrates an internal block diagram of a computer device in one embodiment. The computer device may be, in particular, a server including, but not limited to, a high performance computer and a high performance computer cluster. As shown in fig. 3, the computer device includes a processor, a memory, and a network interface connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store a computer program that, when executed by a processor, causes the processor to implement the transaction distribution method. The internal memory may also have stored therein a computer program which, when executed by the processor, causes the processor to perform the transaction distribution method.
In one embodiment, the transaction distribution method provided by the present invention may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 3. The memory of the computer device may store therein various program templates that make up the item distribution system. Such as: an acquisition unit 1, a matching unit 2, a judgment unit 3, a splitting unit 4, and a binding unit 5.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
according to the reporting information uploaded by the reporting department, according to the corresponding processing matters matched with the reporting information, the processing matters comprise a plurality of processing worksheets, whether each processing worksheet is not matched with a corresponding executing department is judged, if yes, semantic splitting is carried out on the reporting information, so that a plurality of identification characters are generated, and the executing departments of each processing worksheet are matched according to the identification characters.
The method and the device have the advantages that after corresponding processing matters are matched according to the reported information, the execution department for execution is automatically identified according to the matching condition of the processing worksheets and the execution departments contained in the processing matters, when the processing worksheets are not bound with the execution departments, the corresponding execution departments are re-matched according to the identification characters after the reported information is split into identification characters through semantic identification, so that the automatic matching of the execution departments is realized, the problem that the corresponding execution departments cannot be accurately matched due to unclear authority division of the departments is solved, the problems that the processing worksheets contained in the processing matters in the prior art are more, and when the authority division of the execution departments involved in the processing worksheets is not clear enough, communication cooperative efficiency is low between the execution departments are easy to occur, and the processing efficiency of the processing matters is improved.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), and double data rates, among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (7)
1. A transaction distribution method is characterized by comprising the following steps:
reporting information uploaded by a reporting department;
according to the corresponding processing matters matched with the reported information, the processing matters comprise a plurality of processing work orders;
judging whether each processing work order is not matched with a corresponding execution department;
if yes, carrying out semantic splitting on the reported information, so as to split the reported information into adverb characters and main word characters, wherein the adverb characters are adverbs contained in the reported information, and the main word characters are other characters except the adverb characters in the reported information;
marking the main word characters as identification characters, and matching the execution departments of the processing worksheets according to the identification characters;
wherein the step of matching the execution departments of the processing worksheets according to the identification characters further comprises:
acquiring history treatment data of the processing work order, wherein the history treatment data comprises history report information matched with the processing work order, a history source and a history execution department;
training a preset classification model according to the historical treatment data so as to generate a final matching model, inputting the identification characters into the final matching model for calculation, and outputting a final execution department;
binding the final execution department with the processing worksheet matched with the identification character, thereby determining that the processing worksheet is to be executed by the final execution department;
the step of inputting the identification characters into the final matching model for calculation and outputting a final execution department specifically comprises the following steps:
inputting the identification characters into the final matching model for prediction reduction, so as to output a prediction parameter set;
inputting the prediction parameter set into the final matching model again to perform prediction, so as to output final matching characteristics, wherein the final matching characteristics are contained in the identification characters;
matching the corresponding execution departments according to the final matching characteristics;
the step of training a preset classification model according to the historical treatment data so as to generate a final matching model specifically comprises the following steps:
storing the history report information, the history source and the history execution department in a preset training table to serve as a training basis of the preset classification model;
acquiring a preset industry word segmentation dictionary as a model word segmentation basis, wherein the preset industry word segmentation dictionary comprises a plurality of industry classification nouns;
circularly matching the history report information, the history source, the history execution department and the preset industry word segmentation dictionary according to a preset matching mode, and integrating successfully matched characters into a training character set;
and after the characters contained in the training character set are subjected to standardized processing and marked as a model training set, inputting the model training set into the preset classification model for training, so as to generate a final matching model.
2. The item distribution method according to claim 1, wherein said step of matching said execution units of each of said processing worksheets based on said identification characters, specifically comprises:
after each processing work order is switched to a state to be allocated, a first preset word stock matched with the execution department is obtained;
judging whether the number of matches between the identification characters and the first preset word stock exceeds a preset threshold matched with the execution department,
if yes, binding the processing worksheet with the executive department, and determining that the processing worksheet is to be executed by the executive department with successful binding.
3. The item distribution method according to claim 1, wherein after the step of determining whether each of the processing worksheets does not match a corresponding execution department, further comprising:
if not, judging whether part of the processing worksheets are not matched with the corresponding executive departments;
if yes, after each processing work order is switched to a state to be allocated, an execution department successfully matched with the processing work order is acquired and is recorded as a department to be pushed;
acquiring a second preset word stock matched with the department to be pushed;
judging whether the number of matches between the identification characters and the second preset word stock exceeds a preset threshold matched with the execution department,
if yes, binding the processing worksheet with the department to be pushed, and therefore determining that the processing worksheet is executed by the department to be pushed, wherein the department to be pushed is successfully bound.
4. The item distribution method according to claim 1, wherein after the step of determining whether each of the processing worksheets does not match a corresponding execution department, further comprising:
if not, judging whether each processing work order is matched with only one execution department;
if yes, binding the processing worksheet with the executive department, and determining that the processing worksheet is to be executed by the executive department with successful binding.
5. A transaction distribution system, comprising:
the acquisition unit is used for reporting information uploaded by the reporting department;
the matching unit is used for matching corresponding processing matters according to the reported information, wherein the processing matters comprise a plurality of processing worksheets;
the judging unit is used for judging whether each processing work order is not matched with the corresponding execution department;
the splitting unit is used for carrying out semantic splitting on the reported information if the reported information is judged to be the same, so that the reported information is split into adverb characters and main word characters, wherein the adverb characters are adverbs contained in the reported information, and the main word characters are other characters except the adverb characters in the reported information;
the binding unit is used for marking the main word characters as identification characters and matching the execution departments of the processing worksheets according to the identification characters;
the binding unit is configured to record the main word character as an identification character, and match the execution department of each processing work order according to the identification character, and then further includes:
acquiring history treatment data of the processing work order, wherein the history treatment data comprises history report information matched with the processing work order, a history source and a history execution department;
training a preset classification model according to the historical treatment data so as to generate a final matching model, inputting the identification characters into the final matching model for calculation, and outputting a final execution department;
binding the final execution department with the processing worksheet matched with the identification character, thereby determining that the processing worksheet is to be executed by the final execution department;
the step of inputting the identification characters into the final matching model for calculation and outputting a final execution department specifically comprises the following steps:
inputting the identification characters into the final matching model for prediction reduction, so as to output a prediction parameter set;
inputting the prediction parameter set into the final matching model again to perform prediction, so as to output final matching characteristics, wherein the final matching characteristics are contained in the identification characters;
matching the corresponding execution departments according to the final matching characteristics;
the step of training a preset classification model according to the historical treatment data so as to generate a final matching model specifically comprises the following steps:
storing the history report information, the history source and the history execution department in a preset training table to serve as a training basis of the preset classification model;
acquiring a preset industry word segmentation dictionary as a model word segmentation basis, wherein the preset industry word segmentation dictionary comprises a plurality of industry classification nouns;
circularly matching the history report information, the history source, the history execution department and the preset industry word segmentation dictionary according to a preset matching mode, and integrating successfully matched characters into a training character set;
and after the characters contained in the training character set are subjected to standardized processing and marked as a model training set, inputting the model training set into the preset classification model for training, so as to generate a final matching model.
6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the transaction distribution method of any of claims 1 to 4 when the computer program is executed by the processor.
7. A computer-readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the item distribution method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211382886.1A CN115641090B (en) | 2022-11-07 | 2022-11-07 | Item distribution method, system, computer device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211382886.1A CN115641090B (en) | 2022-11-07 | 2022-11-07 | Item distribution method, system, computer device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115641090A CN115641090A (en) | 2023-01-24 |
| CN115641090B true CN115641090B (en) | 2023-11-07 |
Family
ID=84949593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211382886.1A Active CN115641090B (en) | 2022-11-07 | 2022-11-07 | Item distribution method, system, computer device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115641090B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281698A (en) * | 2014-10-15 | 2015-01-14 | 国云科技股份有限公司 | Efficient big data query method |
| CN114066420A (en) * | 2021-11-18 | 2022-02-18 | 建信金融科技有限责任公司 | Work order distribution method, system, electronic equipment and computer readable medium |
| CN114331198A (en) * | 2021-12-31 | 2022-04-12 | 国泰新点软件股份有限公司 | Work order distribution method, equipment and storage medium |
| CN114936727A (en) * | 2022-01-18 | 2022-08-23 | 中国电信集团工会上海市委员会 | Work order distribution system, method and computer equipment |
-
2022
- 2022-11-07 CN CN202211382886.1A patent/CN115641090B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281698A (en) * | 2014-10-15 | 2015-01-14 | 国云科技股份有限公司 | Efficient big data query method |
| CN114066420A (en) * | 2021-11-18 | 2022-02-18 | 建信金融科技有限责任公司 | Work order distribution method, system, electronic equipment and computer readable medium |
| CN114331198A (en) * | 2021-12-31 | 2022-04-12 | 国泰新点软件股份有限公司 | Work order distribution method, equipment and storage medium |
| CN114936727A (en) * | 2022-01-18 | 2022-08-23 | 中国电信集团工会上海市委员会 | Work order distribution system, method and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115641090A (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111506498B (en) | Automatic generation method and device of test case, computer equipment and storage medium | |
| CN109062925B (en) | Method, device, computer equipment and storage medium for automatically generating insert sentences | |
| CN112651238A (en) | Training corpus expansion method and device and intention recognition model training method and device | |
| CN110009347B (en) | Block chain transaction information auditing method and device | |
| CN110019754A (en) | A kind of method for building up of knowledge base, device and equipment | |
| CN112948504B (en) | Data acquisition method and device, computer equipment and storage medium | |
| CN110889272A (en) | Data processing method, device, equipment and storage medium | |
| CN115391439B (en) | Document data export method, device, electronic equipment and storage medium | |
| CN111813946A (en) | Medical information feedback method, device, equipment and readable storage medium | |
| CN108268605B (en) | Shared space resource management method and system | |
| WO2020233310A1 (en) | Asynchronous compensation method and apparatus for real-time processing data, device, and storage medium | |
| CN110275703B (en) | Method and device for assigning key value to data, computer equipment and storage medium | |
| CN110956031A (en) | Text similarity matching method, device and system | |
| CN115641090B (en) | Item distribution method, system, computer device and medium | |
| CN112256844B (en) | Text classification method and device | |
| CN110928941A (en) | Data fragment extraction method and device | |
| CN111831687A (en) | Data query optimization method and device, computer equipment and storage medium | |
| US20200258093A1 (en) | Compliance standards mapping | |
| CN107092671B (en) | Method and equipment for managing meta information | |
| CN114896955A (en) | Data report processing method and device, computer equipment and storage medium | |
| CN114580769A (en) | Material monitoring method and device, computer equipment and medium | |
| CN113901075A (en) | Method and device for generating SQL (structured query language) statement, computer equipment and storage medium | |
| CN112416983B (en) | Data processing method and device and computer readable storage medium | |
| CN111240846A (en) | Data auditing method and device, computer equipment and storage medium | |
| CN111291889B (en) | Knowledge base construction method and device |
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 |