CN115438995A

CN115438995A - Service processing method and equipment for garment customization enterprise based on knowledge graph

Info

Publication number: CN115438995A
Application number: CN202211154954.9A
Authority: CN
Inventors: 张蕴蓝; 闫梅丽; 米庆洋; 刘琦; 艾铮; 陈健宁
Original assignee: Qingdao Kutesmart Co ltd
Current assignee: Qingdao Kutesmart Co ltd
Priority date: 2022-09-21
Filing date: 2022-09-21
Publication date: 2022-12-06
Anticipated expiration: 2042-09-21
Also published as: CN115438995B

Abstract

The embodiment of the specification discloses a service processing method and equipment for a garment customization enterprise based on a knowledge graph, wherein the method comprises the following steps: responding to processing request information of a service to be processed in a corresponding terminal of a clothing customization enterprise, and extracting keywords in the processing request information according to the incidence relation and the vocabulary attributes of each vocabulary in the processing request information; dividing the keywords into different sets to determine function labels to be processed corresponding to the sets; inquiring whether a function label corresponding to the function label to be processed exists in a preset knowledge graph or not; if so, acquiring a person to be selected based on the functional label, and determining department information corresponding to the service to be processed according to the person to be selected; and dividing the execution forms of the sub-services to be processed according to the work content of each department and the personnel authority in each department, storing the execution forms in a preset processing module, and determining the processing forms and the processing sequences of the sub-services to be processed in the services to be processed based on the preset processing module.

Description

Service processing method and equipment for garment customization enterprise based on knowledge graph

Technical Field

The specification relates to the technical field of data processing, in particular to a service processing method and equipment for a garment customization enterprise based on a knowledge graph.

Background

The business process of the garment customization enterprise is carried out in production and operation activities, such as: the method comprises the following steps of financial examination and approval of cloth feeding, training of a sportsman, qualification examination and approval of the sportsman, order delivery of clothes, workshop process flow allocation and the like. The business processing in the clothing customization enterprise is to utilize the staff function resources in the enterprise as high as possible, realize the goals of saving, rapidness, much and good, and obtain the maximum business output efficiency. Therefore, how to effectively process the business is an important process in the production and development process of the garment customization enterprise.

Currently, the common adoption in garment customization enterprises is: and establishing a mapping relation between the business and the staff according to the mode of dividing the functions of the staff based on the departments and the positions. When the business needs to be processed, the corresponding department and the corresponding position are searched to determine the processing staff of the business, and then the staff executes the corresponding business processing according to the subjective deployment flow or the fixed business execution flow. The traditional mode of distributing the to-be-processed service based on the positions cannot fully mobilize the employees of the enterprise, so that the function of the employees cannot be maximized, and meanwhile, the flow and the sequence of the service processing cannot be flexibly deployed based on the department and the position for the solidification of the personnel structure in the enterprise, so that the problems of low efficiency and difficult cost regulation and control in the service processing process are caused.

Disclosure of Invention

One or more embodiments of the present specification provide a service processing method and device for a garment customization enterprise based on a knowledge graph, so as to solve the following technical problems: how to provide an efficient enterprise business processing method.

One or more embodiments of the present disclosure adopt the following technical solutions:

one or more embodiments of the present specification provide a service processing method for a garment customization enterprise based on a knowledge graph, the method including:

responding to processing request information of a service to be processed in a terminal corresponding to a clothing customization enterprise, and extracting keywords in the processing request information according to the incidence relation among vocabularies in the processing request information and the attributes of the vocabularies;

dividing the keywords into different sets according to the task categories corresponding to the keywords to generate corresponding function sets, and determining one or more to-be-processed function labels corresponding to the function sets according to the keywords in the function sets;

inquiring whether a function label corresponding to the function label to be processed exists in a preset knowledge map stored in a clothing customizing enterprise database;

if the corresponding functional label is inquired, obtaining information of a person to be selected corresponding to the service to be processed in the preset knowledge graph based on the corresponding functional label, and determining department information corresponding to the service to be processed according to the information of the person to be selected;

according to the work content of each relevant department in the department information corresponding to the to-be-processed service and the personnel processing authority in each department, dividing the execution form of each to-be-processed sub-service corresponding to the to-be-processed service into multi-department cooperative service or single-department execution service, and storing the execution form in a preset processing module so as to determine the processing form and the processing sequence of each to-be-processed sub-service in the to-be-processed service based on the preset processing module.

Optionally, in one or more embodiments of the present specification, before querying whether a function tag corresponding to the to-be-processed function tag exists in a preset knowledge graph of a garment customization enterprise, the method further includes:

acquiring the working content of each person in the clothing customizing enterprise based on the historical business processing data of the clothing customizing enterprise;

splitting the working content based on the type of the working content, determining the particle function corresponding to each person, and establishing a first connection relation between the person and the particle function;

determining at least one function label of the particle function according to the work content contained in the particle function, and establishing a second connection relation between the particle function and the function label;

acquiring an organization architecture of the clothing customizing enterprise, and acquiring a third connection relation between each person and each department in the clothing customizing enterprise according to the organization architecture of the clothing customizing enterprise;

and respectively establishing mapping connection between the personnel and the particle function, between the particle function and the function label and between the personnel and each department in the clothing customization enterprise based on the first connection relation, the second connection relation and the third connection relation, and constructing the knowledge graph of the clothing customization enterprise.

Optionally, in one or more embodiments of the present specification, before responding to processing request information of a service to be processed in a corresponding terminal of a clothing customization enterprise, to extract a keyword in the processing request information according to an association relationship between words in the processing request information and attributes of the words, the method further includes:

acquiring an uploading form of the processing request information, and if the processing request information is determined to be in a voice uploading form based on the uploading form, converting the processing request information into character information through a corresponding conversion tool;

inputting the character information and preset business processing vocabulary data of the clothing customization enterprise into a preset grammar checking model so as to check the grammar of the character information and obtain a checking result of the character information;

if the word information is determined to pass grammar verification based on the verification result, the word information is used as the text information of the processing request information;

if the word information is determined to not pass grammar verification based on the verification result, determining a service type corresponding to the processing request based on the word information;

dividing the text information into a plurality of fields, and determining adjacent words in each field so as to divide the fields into a first field with semantic error and a second field without semantic error based on the adjacent words and the service type;

acquiring a candidate field corresponding to the second field according to the service type, and acquiring pinyin corresponding to the second field and pinyin of the candidate field;

constructing a similarity matrix between the second field and the candidate field according to the characters of the pinyins corresponding to the second field and the characters of the pinyins of the candidate field and the similarity between the tones of the pinyins corresponding to the second field and the tones of the pinyins of the candidate field;

determining a field with the highest similarity in the candidate fields based on the similarity matrix, and taking the field with the highest similarity as a replacement field of the second field;

and correcting the second field based on the replacement field to obtain text information of the processing request, so that keywords extracted based on the text information are used as keywords in the processing request information.

Optionally, in one or more embodiments of the present specification, extracting a keyword in the processing request information according to an association relationship between vocabularies in the processing request information and attributes of the vocabularies specifically includes:

sentence segmentation is carried out on the sentences in the processing request information through preset sentence segmentation marks, and the serial numbers of the sentences in the processing request information are obtained;

determining words contained in the processing request information according to a word segmentation dictionary preset by the clothing customization enterprise;

acquiring attributes corresponding to all vocabularies, filtering the vocabularies irrelevant to the processing request based on the corresponding attributes, and acquiring initial vocabularies of the processing request information;

performing joint iteration of association relation on the initial vocabulary according to the serial number of the sentence corresponding to the association rule and the initial vocabulary to obtain a frequent vocabulary set of the processing request information, and generating a corresponding sliding window parameter according to the frequent vocabulary set so as to mark the vocabulary in the same window based on the sliding window parameter;

calculating an associated entropy value contained in each vocabulary according to a definition rule of associated entropy and the mark, obtaining the existence probability of the vocabulary in each frequent vocabulary set, and determining an associated entropy weight value of the vocabulary according to the existence probability;

calculating an average associated entropy weight value of the vocabularies in each frequent vocabulary set according to the associated entropy weight value of each vocabulary, and determining the weight value of each vocabulary based on the average associated entropy weight value;

and acquiring a link matrix of each frequent vocabulary set to iteratively calculate the weight value of the vocabulary, and if the weight value converges to a preset credible threshold interval, sequencing the weight values of the vocabularies to obtain a preset number of vocabularies serving as keywords of the processing request information.

Optionally, in one or more embodiments of the present specification, after querying a preset knowledge graph stored in a database of a clothing customization enterprise to determine whether a function tag corresponding to the function tag to be processed exists, the method further includes:

if the functional label is not inquired, extracting statement information related to business processing in the processing request information;

acquiring historical query services of a terminal corresponding to the processing request information, and determining a target scene of the service to be processed based on the statement information and the historical query services;

determining at least one to-be-selected scene intention corresponding to the target scene based on the incidence relation between a preset service processing scene and the scene intention;

screening the at least one scene intention to be selected according to the processing request information and the last processing service of the terminal where the processing request is positioned, and determining the scene intention of the service to be processed;

and determining department information corresponding to the to-be-processed service according to the basic information of the to-be-processed sub-service corresponding to the scene intention and the range information of the processing personnel in the clothing customization enterprise corresponding to the to-be-processed sub-service.

Optionally, in one or more embodiments of the present specification, before determining at least one candidate scene intention corresponding to the target scene based on an association relationship between a preset service processing scene and a scene intention, the method further includes:

creating at least one business processing scene related to the clothing customizing enterprise according to the historical business data of the clothing customizing enterprise; wherein the service processing scenario at least comprises any one or more of the following: the method comprises the following steps of (1) carrying out qualification approval scene of a sportsman, service evaluation scene of the sportsman, scene of applying for a garment processing order, scene of measuring and dispatching a order, and scene of cloth quality auditing;

acquiring processing flow information of each service in the clothing customization enterprise according to the historical service data, and configuring corresponding to-be-processed sub-services for the service processing scene based on the processing flow information;

acquiring basic processing tasks of the sub-services to be processed and personnel range information related to processing personnel, integrating the basic processing tasks and the personnel range information to acquire scene intents of the sub-services to be processed in the service processing scene, and establishing an association relationship between the service processing scene and the scene intents.

Optionally, in one or more embodiments of the present specification, according to the work content of each department in the department information corresponding to the to-be-processed service and the personnel processing authority in each department, dividing the execution form of each to-be-processed sub-service in the to-be-processed service into a multi-department collaborative service or a single-department execution service, specifically including:

determining that the to-be-processed service belongs to an accessory customization service or a full-garment customization service according to the processing request information, and acquiring the to-be-processed sub-service corresponding to the accessory customization service or the full-garment customization service; wherein the accessory customization service at least comprises any one or more of the following: related business is customized by buttons, related business is customized by waistbands, and related business is customized by disk buttons;

according to the clothing customizing work content corresponding to each department, matching each sub-business to be processed in the accessory customizing business or the whole clothing customizing business with the clothing customizing work corresponding to each department respectively so as to determine department information corresponding to each sub-business to be processed in the business to be processed respectively;

if it is determined that each sub-service to be processed in the sub-services to be processed corresponds to a single department according to the department information corresponding to the sub-services to be processed, acquiring personnel processing authority in the department, and determining that the execution form of the sub-services to be processed is a single-department serial service or a single-department parallel service based on the personnel processing authority;

and if the sub-task service to be processed corresponds to a plurality of departments according to the department information corresponding to the sub-service to be processed, acquiring the personnel processing permission of each department, and determining the execution form of the sub-service to be processed to be a multi-department parallel cooperative service or a multi-department serial cooperative service based on the personnel processing permission.

Optionally, in one or more embodiments of the present specification, after dividing an execution form of each sub-service to be processed in the service to be processed into a multi-department collaborative service or a single-department execution service according to work content of each department in the department information corresponding to the service to be processed and a person processing authority in each department, the method further includes:

if the sub-service to be processed is determined to be a multi-department parallel collaborative service or a single-department parallel service according to the work content of the clothing customization corresponding to the multiple departments and the personnel processing permission in each department, a parallel customization thread is established for the sub-service to be processed; storing the sub-services to be processed into a preset processing module so as to sequentially determine the processing form of the sub-services to be processed in the services to be processed based on the preset processing module;

if the sub-service to be processed in the service to be processed is determined to be a multi-department serial cooperative service or a single-department serial service according to the work content of the multiple departments and the personnel processing authority in each department, acquiring the incidence relation of each work task in the sub-service to be processed according to the incidence relation of the multiple departments;

and determining a front sub-service and a rear sub-service of each sub-service to be processed according to the incidence relation of each work task in the sub-services to be processed, and storing the sub-services to be processed, the front sub-service and the rear sub-service into a preset processing module so as to determine the processing form and the processing sequence of each sub-service to be processed in the services to be processed based on the preset processing module.

Optionally, in one or more embodiments of the present specification, after determining, based on the preset processing module, a processing form and a processing sequence of each to-be-processed sub-service in the to-be-processed service, the method further includes:

determining a business processing flow of the to-be-processed task in the clothing customizing enterprise based on the processing form and the processing sequence of each to-be-processed sub-business in the to-be-processed task so as to obtain at least one clothing production link corresponding to the business processing flow in the clothing customizing enterprise;

determining information of a plurality of persons to be processed corresponding to the at least one garment production link in the persons to be selected and a plurality of business processing stages corresponding to the at least one production link according to the garment detail design requirement information and the garment cutting process information in the processing request information;

obtaining grades of a plurality of to-be-processed employees corresponding to the at least one garment production link, inputting the grades of the plurality of to-be-processed employees and technical cost data of the business processing stages into a preset cost prediction model, obtaining the cost of the to-be-selected employee in different business processing stages, and determining a first weight value of the to-be-selected employee according to the cost; wherein the cost is in an inverse relationship with the first weight value;

acquiring a time interval between idle time and current time of a to-be-processed person corresponding to the at least one garment production link, and determining a second weight value of the to-be-processed person based on the time interval; wherein the time interval is in an inverse relationship with the second weight value;

and taking the weighted value of the first weighted value and the second weighted value as the weighted value of the to-be-processed personnel, and determining personnel information with the highest matching degree in the to-be-processed personnel in the at least one clothing production link based on the weighted value so as to assist in judging the execution link information and the execution personnel information of the to-be-processed business.

One or more embodiments of the present specification provide a business process apparatus for a knowledge-graph based garment customization enterprise, the apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform:

responding to processing request information of a service to be processed in a corresponding terminal of a clothing customization enterprise, and extracting keywords in the processing request information according to the incidence relation among vocabularies in the processing request information and the attributes of the vocabularies;

inquiring whether a function label corresponding to the function label to be processed exists in a preset knowledge map stored in a clothing customization enterprise database;

The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:

in the description, after the query request is converted into the text information, the keywords in the text information are extracted for subsequent query, so that the query efficiency is improved, the query mode is unified, convenience is brought to text error correction of the query request, and the accuracy of service processing is improved. The keywords are divided into function sets according to the task categories to which the keywords belong, so that the function labels of the function sets are determined, the corresponding staff are determined by inquiring the function labels through the knowledge graph, and the problems that the functions of the staff are solidified based on departments and posts in the traditional mode, so that the functions of the staff cannot be fully utilized and the functions of the staff are mined are solved. Meanwhile, based on the analysis of the scene intention on the query request, the possibility of wrong distribution of the service to be processed caused by unclear subjective description of a service inquirer is reduced, and the efficiency of service processing is improved.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the description below are only some embodiments described in the present specification, and for those skilled in the art, other drawings may be obtained according to these drawings without creative efforts. In the drawings:

fig. 1 is a schematic flowchart of a method for processing services of a clothing customization enterprise based on a knowledge graph according to an embodiment of the present disclosure;

fig. 2 is a schematic diagram of an architecture of a knowledge-graph-based enterprise business processing process in an application scenario according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of an internal structure of an enterprise business processing apparatus based on a knowledge graph according to an embodiment of the present disclosure.

Detailed Description

The embodiment of the specification provides a service processing method and equipment for a garment customization enterprise based on a knowledge graph.

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present specification without any creative effort shall fall within the protection scope of the present specification.

As shown in fig. 1, an embodiment of the present specification provides a method flow diagram of a service processing method of a clothing customization enterprise based on a knowledge graph, as can be seen from fig. 1, the method includes the following steps:

s101: responding to processing request information of a service to be processed in a corresponding terminal of a clothing customizing enterprise, and extracting keywords in the processing request information according to the incidence relation among all vocabularies in the processing request information and the attributes of all the vocabularies.

Enterprises may encounter, for example, in the course of production and operation: in order to improve the query speed of the query staff of the to-be-processed business, the to-be-processed business needs to be distributed to corresponding staff for processing. In the embodiment of the present specification, the server responds to the query request of the service to be processed initiated by the querier, and after the query request is obtained, the server processes the association relationship between the vocabularies and the attributes of the vocabularies in the request information, and extracts the keywords in the processing request information, so as to perform subsequent processing based on the keywords, thereby improving the query efficiency.

Further, since the query request may be based on a voice query or a text query, in order to facilitate uniform processing and analysis of the server, before the server extracts the keywords in the processing request information according to the association relationship between the vocabularies in the processing request information and the attributes of the vocabularies, the method further includes the following steps: firstly, acquiring the uploading form of the processing request information, and if the uploading form of the processing request information is determined to be the voice uploading form, converting the processing request information into the text information through a corresponding conversion tool. For example: in the voice query form, the voice needs to be converted into the text information, and the text information can be converted in the NLP mode, and the text conversion tool is not limited here. Because semantic errors and other problems may exist in the conversion process or when the inquirer uploads the processing request information, the accuracy of the business processing is improved. Firstly, inputting the character information corresponding to the converted processing request information and preset business processing vocabulary data of the clothing customization enterprises into a preset grammar checking model, so as to check the grammar of the character information and obtain the checking result of the character information. It should be noted that the preset service processing vocabulary data stores language information corresponding to each service processed in the clothing customization enterprise, and as shown in fig. 2, in the application scenario of the present specification, the operations such as analyzing text information and training a preset grammar check model can be implemented based on the AI capability layer.

And if the character information can be determined to pass the grammar check according to the check result obtained in the check process, the character information is used as the text information after the processing request information is converted. And if the check result obtained according to the process can confirm that the text information does not pass the grammar check, determining the service type corresponding to the processing request information according to the text information. And then dividing the text information into a plurality of fields, and determining adjacent words in each field, so that the fields are divided into a first field with semantic errors and a second field without semantic errors based on the adjacent words and the service field. For example: and if the text information is 'beam qualification approval of the clothing sportsman', roughly determining that the service type corresponding to the query request is 'approval' field according to the text information. Then dividing the fields into a plurality of fields of 'clothing', 'sportsman's 'beam body', 'qualification' and 'approval' according to the text information, determining that the fields of 'clothing', 'sportsman's 'qualification' and 'approval' are first fields without semantic errors according to adjacent words and the affiliated approval field, and determining that the fields are second fields with semantic errors because the beam body is not matched with the adjacent words and the business field. And then acquiring a candidate field corresponding to the second field according to the service field, and acquiring the pinyin corresponding to the second field and the pinyin of the candidate field. And constructing a similarity matrix between the second field and the candidate field according to the characters of the pinyins corresponding to the second field and the characters of the pinyins of the candidate field and the similarity between the tones of the pinyins corresponding to the second field and the tones of the pinyins of the candidate field. And determining a field with the highest similarity with the second field in the candidate fields according to the similarity matrix, and then taking the field with the highest similarity as a replacement field of the second field. And correcting the second field according to the determined alternative field, thereby obtaining the text information converted by the query request. By correcting the text information, errors caused by subjective query of a querier and semantic errors caused in the process of converting the text information into the text information based on a conversion tool are reduced, and the accuracy of service processing and subsequent distribution is improved.

Further, in order to avoid the problem that the vocabulary with the large occurrence number is determined as the keyword only based on the occurrence number of the vocabulary in the traditional mode, the problem that the vocabulary with the small occurrence number but with important significance is ignored is caused. In one or more embodiments of the present specification, extracting keywords in text information according to an association relationship between words in processing request information and attributes of the words specifically includes the following steps:

firstly, sentence division is carried out on sentences in processing request information through preset sentence division marks, and numbers corresponding to the sentences in the processing request information are obtained. Such as: the text information corresponding to the processed query request in a certain scene is as follows: the method comprises the steps that firstly, available clothing designer information of each department needs to be collected, then corresponding butt-joint persons are determined according to clothing customization requirements, related persons are organized to process clothing customization orders, and orders are dispatched to produce, then text information is divided into preset sentence division marks, for example, "/" is used as a sentence division mark, the text information is divided into "the clothing customization scheme and the clothing customization orders of the first department need to be processed at present,"/"is required to be processed, firstly, the available clothing designer information of each department needs to be collected,"/is used for determining the corresponding butt-joint persons according to the clothing customization requirements, "/is organized to be related persons to process clothing customization orders/dispatches to produce," the clothing customization scheme and the clothing customization orders of the first department need to be processed, "/" is corresponding to the sentence number 1, ", the available clothing designer information of each department needs to be collected,"/"is corresponding to the sentence number 2, and the numbers corresponding to the sentences are obtained sequentially.

After the sentences are divided, the words contained in the processing request information are determined according to a word segmentation dictionary preset by the clothing customization enterprise. And then acquiring attributes corresponding to all the vocabularies, filtering the vocabularies irrelevant to the processing request based on the corresponding attributes, and acquiring initial vocabularies of the processing request information. Taking "the available costume designer information of each department needs to be collected first" as an example, it can be seen that the words of "first", "need", and "are words unrelated to the query request, and need to be filtered, so as to obtain the initial words of the text information. And then performing joint iteration of association relation on the initial vocabulary according to the association rule and the number of the sentence corresponding to the initial vocabulary to obtain a frequent vocabulary set of the processing request information, and generating corresponding sliding window parameters according to the frequent vocabulary set, thereby marking the vocabulary in the same window according to the parameters of the sliding window. And then, calculating a correlation entropy value contained in each vocabulary according to a definition rule and a mark of the correlation entropy, obtaining the existence probability of the vocabulary in each frequent vocabulary set, and determining a correlation entropy weight value of the vocabulary according to the existence probability. And then, calculating the average associated entropy weight value of the words in each frequent word set according to the associated entropy weight value of each word, thereby determining the weight value of each word according to the obtained average associated entropy weight value. And acquiring a link matrix of each frequent vocabulary set, thereby iteratively calculating the weight value of the vocabulary, and sequencing the weight values of the vocabularies if the weight values of the vocabularies are determined to be converged within a preset credible threshold interval range, so as to obtain the vocabularies of a preset number as keywords for processing the request information.

S102: dividing the keywords into different sets according to the task categories corresponding to the keywords to generate corresponding function sets, and determining one or more to-be-processed function labels corresponding to the function sets according to the keywords in the function sets.

Based on the keywords of the processing request information obtained in step S101, in order to facilitate quick query of service executors, in this embodiment of the present specification, the keywords are divided into different function sets according to task categories corresponding to the keywords, and then at least one function label corresponding to each function set is determined according to the keywords in the function sets. For example, the processing request information in step S101 is "currently received a clothing customization scheme and a clothing customization order of a company a needs to be processed/firstly, available clothing designer information of each department needs to be collected/then a corresponding dockee is determined according to the clothing customization requirement,/an organization related person processes the clothing customization order/dispatches the order to produce", if the obtained keywords after processing are "collection", "department", "clothing designer information", "clothing customization requirement", "dockee", "organization", "processing", "order", "dispatches", "production", the keywords are classified into sets of "collection, department, clothing designer information", "collection, clothing customization requirement", "dockee", "organization, processing, order", "order, dispatches, production", and the like according to the task category of each keyword, and then the function label of each set is obtained as the function label to be queried based on the keyword in each set.

S103: and inquiring whether a function label corresponding to the function label to be processed exists in a preset knowledge graph stored in a clothing customization enterprise database.

The problem that the functions of staff cannot be fully excavated due to the fact that business processing is distributed based on fixed posts in the traditional mode is solved, and the problem that business processing efficiency and cost are high is further solved. In one or more embodiments of the present description, by querying a preset knowledge graph of a garment customization enterprise, it is determined whether a function tag corresponding to a function tag to be queried exists for querying, and a manner of querying based on the function tag breaks through an inherent employee framework when performing service matching based on employee positions, which brings beneficial effects for improving efficiency of enterprise service processing and saving processing cost. Among them, it should be noted that: the knowledge graph is used as a new knowledge organization and retrieval technology in the big data era and is used for describing concepts and mutual relations in the physical world in a symbolic form. The basic composition unit is an entity-relation-entity triple, an entity and related attribute value-value pairs thereof, and the entities are mutually connected through relations to form a network knowledge structure. Through a man-machine interaction technology, a large amount of computer readable knowledge can be obtained, and the query efficiency is improved by using the powerful information retrieval function of the knowledge graph in the embodiment of the specification. As shown in fig. 2, the knowledge layer implements knowledge acquisition and database mapping, processes data and automatically extracts knowledge, generates structured information, and stores the structured information in a knowledge graph to manage and maintain entity attributes and association relationships.

Further, in one or more embodiments of the present specification, before querying whether a function tag corresponding to a function tag to be queried exists in a preset knowledge graph of a garment customization enterprise, the method further includes the following processes: firstly, processing data according to the historical business of the clothing customization enterprise, and obtaining the work content of each person. And then splitting each working content according to the type of the working content, determining the particle function corresponding to each person, and establishing a first connection relation between the staff and the particle function. It should be noted that the particle function is a micro-service item that can be handled by each employee, for example: the basic abilities and functions of the employee, such as retrieval ability, pseudo-approval ability, financial approval ability, project docking ability, and the like, are considered to be the granular functions of the employee. And then determining at least one function label of the particle function according to the work content contained in the particle function of the employee, and establishing a second connection relation between the particle function and the function label. Wherein, it is to be noted that the functional label is a label for describing the function of the particle.

And then acquiring an organization architecture of the clothing customizing enterprise, acquiring a third connection relation between each person and each department in the clothing customizing enterprise according to the organization architecture of the clothing customizing enterprise, and respectively establishing mapping connection between the person and the particle function, the particle function and the function label and between the person and each department in the clothing customizing enterprise according to the first connection relation, the second connection relation and the third connection relation, so as to establish a knowledge graph of the connection relation between the function label and the particle function in the clothing customizing enterprise and between the particle function and the staff, between the staff and the department.

Further, in one or more embodiments of the present specification, if the preset knowledge graph is determined based on the above steps, the function tag to be queried determined in the above step S102 cannot be queried. And then extracting statement information related to service processing in the processing request information, acquiring historical query service of the terminal corresponding to the processing request information, and determining a target scene of the service to be processed according to the statement information and the historical query service. And determining at least one intention of the scene to be selected corresponding to the target scene according to the incidence relation between the service processing scene and the scene intention determined in the process. And then screening the determined at least one scene intention to be selected according to the processing request information and the last processing service of the terminal where the processing request is located, so as to determine the scene intention of the service to be processed corresponding to the service processing flow. After the scene intention is determined, at least one function label of the to-be-processed business is determined according to the basic information of the to-be-processed sub-business corresponding to the scene intention and the range information of processing personnel in the clothing customizing enterprise corresponding to the to-be-processed sub-business. And then acquiring the person to be selected corresponding to the service to be processed in the preset knowledge graph according to the corresponding at least one functional label. When the corresponding label cannot be determined based on the processing request information, the embodiment of the specification performs combined analysis based on the scene intention to determine the corresponding functional label, so that the intelligent level of business processing is improved, and the effect of combined analysis with the scene is achieved.

S104: if the corresponding function label is inquired, obtaining information of a person to be selected corresponding to the service to be processed in the preset knowledge graph based on the corresponding function label, and determining department information corresponding to the service to be processed according to the information of the person to be selected.

If the function label to be queried determined in the step S102 can be queried based on the preset knowledge graph in the step S103. In this embodiment of the present specification, a corresponding particle function is obtained according to a function tag corresponding to a function tag to be queried in a preset knowledge graph, and then one or more pieces of information of a person to be selected corresponding to a service to be processed are obtained based on the function particle. The functions of personnel in the clothing customization enterprise are divided and defined based on the particle function mode, so that the full utilization of the capability of the personnel is realized, and the benefit of business processing is improved.

Further, in one or more embodiments of the present specification, before determining at least one candidate scene intention corresponding to a target scene based on an association relationship between a preset service processing scene and a scene intention, the method further includes the following steps: firstly, at least one business processing scene related to the clothing customizing enterprise is created according to the historical business data of the clothing customizing enterprise. It should be noted that the service processing scenario at least includes any one or more of the following: the method comprises the following steps of a qualification approval scene of a sportsman, a service evaluation scene of the sportsman, a scene of applying for a garment processing order, a scene of measuring and dispatching a order, and a scene of cloth quality auditing. And then, acquiring processing flow information of each service in the clothing customization enterprise according to the historical service data, and configuring corresponding to-be-processed sub-services for the service processing scene according to the processing flow information. After the sub-services to be processed are determined, the basic items of each sub-service to be processed and the staff scope information of the processing staff involved in each sub-service to be processed are obtained, where the staff scope information may be department information, such as: if the pending subtask involves a financial transaction, the staff of the processing staff is restricted to the financial department due to the privacy of the financial information. And then, integrating the basic matters with the personnel scope information to obtain the scene intention of each sub-service to be processed in the service processing scene, and establishing the incidence relation between the service processing scene and the scene intention.

S105: according to the work content of each relevant department in the department information corresponding to the to-be-processed service and the personnel processing authority in each department, dividing the execution form of each to-be-processed sub-service corresponding to the to-be-processed service into multi-department cooperative service or single-department execution service, and storing the execution form in a preset processing module so as to determine the processing form and the processing sequence of each to-be-processed sub-service in the to-be-processed service based on the preset processing module.

In order to implement efficient processing of a service to be processed, after determining department information corresponding to information of a person to be selected based on the above process, in the embodiments of the present specification, according to work content of each relevant department in the department information corresponding to the service to be processed and a person processing authority in each department, an execution form of each sub-service to be processed corresponding to the service to be processed is divided into a multi-department collaborative service or a single-department execution service, and the execution form is stored in a preset processing module, so that a processing form and a processing order of each sub-service to be processed in the service to be processed are determined according to the preset processing module in a service processing process, thereby improving processing efficiency of the service to be processed.

Specifically, in one or more embodiments of the present specification, according to the work content of each department in the department information corresponding to the to-be-processed service and the personnel processing authority in each department, the execution form of each to-be-processed sub-service in the to-be-processed service is divided into a multi-department collaborative service or a single-department execution service, which specifically includes:

and determining that the service to be processed belongs to the accessory customization service or the full-length clothes customization service according to the processing request information. Then acquiring a to-be-processed sub-service corresponding to the accessory customization service or the full-garment customization service; it should be noted that the accessory customization service at least includes any one or more of the following: button customization related business, waistband customization related business and coil button customization related business. And according to the clothing customization work content corresponding to each department, matching each sub-business to be processed in the accessory customization business or the whole clothing customization business with the clothing customization work corresponding to each department respectively so as to determine department information corresponding to each sub-business to be processed in the business to be processed respectively. And if the sub-services to be processed in the services to be processed are determined to be executed by a single department, namely, the sub-services to be processed correspond to the single department according to the department information corresponding to the sub-services to be processed, acquiring the personnel processing authority in the department, and determining that the execution form of the sub-services to be processed is a single-department serial service or a single-department parallel service based on the personnel processing authority in the department. And if the sub-task service to be processed corresponds to a plurality of departments according to the department information corresponding to the sub-service to be processed, acquiring the personnel processing authority of each department, and determining the execution form of the sub-service to be processed as the multi-department parallel cooperative service or the multi-department serial cooperative service based on the personnel processing authority.

Further, in order to enable each service to be processed in order according to the corresponding processing form, in one or more embodiments of the present specification, after dividing the execution form of each sub-service to be processed in the service to be processed into a multi-department collaborative service or a single-department execution service according to the work content of each department in the department information corresponding to the service to be processed and the personnel processing authority in each department, the method further includes the following steps:

if the sub-service to be processed is determined to be a multi-department parallel collaborative service or a single-department parallel service according to the work content of the clothing customization corresponding to the multiple departments and the personnel processing permission in each department in the process, a parallel customization thread is established for the sub-service to be processed. And then storing the sub-services to be processed into a preset processing module so as to sequentially determine the processing form of the sub-services to be processed in the services to be processed based on the preset processing module. If the sub-service to be processed in the service to be processed is determined to be a multi-department serial cooperative service or a single-department serial service according to the work content of a plurality of departments and the personnel processing permission of each department, acquiring the incidence relation of each work task in the sub-service to be processed according to the incidence relation of the plurality of departments corresponding to the service. Therefore, the pre-positioned sub-service and the post-positioned sub-service of each sub-service to be processed are determined according to the incidence relation of each work task in the sub-services to be processed, and the sub-services to be processed, the pre-positioned sub-service and the post-positioned sub-service are stored in the preset processing module, so that the processing form and the processing sequence of each sub-service to be processed in the services to be processed are determined based on the preset processing module. As shown in fig. 2, the storage layer may store and process various types of data, store structured data through MySQL, store unstructured data using ES, store map class data using a map database, cache data using Redis, and implement message queue management through kafka. The preset processing mode in this embodiment may be stored based on the storage layer to implement the business processing in order.

Further, in order to assist in determining at least one garment production link, processing efficiency of a garment customization enterprise is improved. In one or more embodiments of the present specification, after determining, based on a preset processing module, a processing form and a processing sequence of each to-be-processed sub-service in the to-be-processed service, the method further includes the following steps:

firstly, according to the processing form and the processing sequence of each sub-service to be processed in the task to be processed, the service processing flow of the service to be processed in the clothing customizing enterprise is determined, and therefore at least one clothing production link corresponding to the service processing flow in the clothing customizing enterprise is obtained. And then according to the clothing detail design requirement information and the clothing cutting process information in the processing request information, determining a plurality of pieces of information of the personnel to be processed corresponding to at least one clothing production link in the personnel to be selected and a plurality of business processing stages corresponding to at least one production link. The method comprises the steps of obtaining grades of a plurality of to-be-processed workers corresponding to at least one clothing production link, inputting the grades of the plurality of to-be-processed workers and technical cost data of business processing stages into a preset cost prediction model, obtaining the cost of the to-be-selected workers in different business processing stages, and determining a first weight value of the to-be-selected workers according to the cost. It can be understood that the cost is in an inverse relationship with the first weight value, that is, the higher the cost is, the lower the first weight value of the person to be selected is, and the lower the cost is, the higher the first weight value of the person to be selected is.

And secondly, acquiring the time interval between the idle time and the current time of the to-be-processed person corresponding to at least one garment production link, and determining a second weight value of the to-be-processed person according to the time interval. It is to be understood that the time interval is inversely proportional to the second weight value, i.e., the shorter the time interval, the higher the second weight value, and the longer the interval, the lower the second weight value. And multiplying the first weight value and the second weight value to obtain a weighted value, taking the weighted value as the weighted value of the to-be-selected person, determining executive personnel information under the comprehensive consideration of cost and efficiency in the to-be-selected person based on the weighted value, and assisting in judging the executive link information and the executive personnel information of the to-be-processed service to realize the efficient processing of the to-be-processed service. It should be further noted that, in the process of using the method, the application layer and the access layer shown in fig. 2 are used to implement the docking with the intelligent application and the implementation of the function, where the access layer mainly completes the docking with the external platform and is based on an open API interface. The small platform program and the large digital screen realize the butt joint of the search and associated recommendation capability of the intelligent knowledge map, the butt joint of the voice recognition and the voice synthesis capability. The application layer supports various intelligent applications of the application system, including knowledge map search, knowledge map data viewing, knowledge question answering, voice query and voice filling capacity, and provides an API interface for capacity output, and related AI capacity can be called through the API interface.

In one or more embodiments of the present description, as shown in fig. 3, a schematic diagram of an internal structure of an enterprise business processing device based on a knowledge graph is provided. As can be seen from fig. 3, the apparatus comprises: a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform:

according to the work content of each relevant department in the department information corresponding to the to-be-processed service and the personnel processing authority in each department, dividing the execution form of each to-be-processed sub-service corresponding to the to-be-processed service into multi-department cooperative service or single-department execution service, and storing the execution form in a preset processing module so as to determine the processing form and the processing sequence of each to-be-processed sub-service in the to-be-processed service based on the preset processing module. All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the apparatus, the device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and for the relevant points, reference may be made to the partial description of the embodiments of the method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The above description is merely one or more embodiments of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments of the present description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A service processing method for a garment customization enterprise based on a knowledge graph is characterized by comprising the following steps:

2. The service processing method of a clothing customization enterprise based on a knowledge graph as claimed in claim 1, wherein before the querying whether the function tag corresponding to the function tag to be processed exists in the preset knowledge graph of the clothing customization enterprise, the method further comprises:

based on the historical business processing data of the clothing customizing enterprise, acquiring the working content of each person in the clothing customizing enterprise;

3. The method as claimed in claim 1, wherein before extracting the keywords from the processing request information according to the association relationship between the vocabularies in the processing request information and the attributes of the vocabularies, the method further comprises:

acquiring an uploading form of the processing request information, and if the processing request information is determined to be a voice uploading form based on the uploading form, converting the processing request information into text information through a corresponding conversion tool;

if the word information is determined not to pass grammar verification based on the verification result, determining the service type corresponding to the processing request based on the word information;

obtaining a candidate field corresponding to the second field according to the service type, and obtaining pinyin corresponding to the second field and pinyin of the candidate field;

4. The service processing method of a knowledge-graph-based clothing customization enterprise according to claim 1, wherein extracting keywords from the processing request information according to an association relationship between words and phrases in the processing request information and attributes of the words and phrases specifically comprises:

performing joint iteration of incidence relation on the initial vocabulary according to the number of the sentence corresponding to the incidence rule and the initial vocabulary, obtaining a frequent vocabulary set of the processing request information, generating a corresponding sliding window parameter according to the frequent vocabulary set, and marking the vocabulary in the same window based on the sliding window parameter;

and acquiring a link matrix of each frequent vocabulary set to iteratively calculate the weight value of the vocabulary, and sequencing the weight values of the vocabularies if the weight values converge to a preset credible threshold interval, so as to acquire a preset number of vocabularies serving as keywords of the processing request information.

5. The service processing method of a clothing customization enterprise based on a knowledge graph as claimed in claim 1, wherein after querying a preset knowledge graph stored in a clothing customization enterprise database to determine whether a functional tag corresponding to the functional tag to be processed exists, the method further comprises:

determining at least one scene intention to be selected corresponding to the target scene based on the incidence relation between the preset service processing scene and the scene intention;

screening the at least one scene intention to be selected according to the processing request information and the last processing service of the terminal where the processing request is located, and determining the scene intention of the service to be processed;

6. The service processing method of the knowledge-graph-based clothing customization enterprise according to claim 5, wherein before determining at least one candidate scenario intention corresponding to the target scenario based on an incidence relation between a preset service processing scenario and a scenario intention, the method further comprises:

acquiring a basic processing task of each sub-service to be processed and personnel scope information related to processing personnel, integrating the basic processing task and the personnel scope information to acquire a scene intention of each sub-service to be processed in the service processing scene, and establishing an association relationship between the service processing scene and the scene intention.

7. The service processing method of a knowledge-graph-based clothing customization enterprise according to claim 1, wherein the dividing of the execution form of each sub-service to be processed in the service to be processed into a multi-department collaborative service or a single-department execution service according to the work content of each department in the department information corresponding to the service to be processed and the personnel processing permission in each department specifically comprises:

and if the sub-task service to be processed corresponds to a plurality of departments according to the department information corresponding to the sub-service to be processed, acquiring personnel processing authorities of all the departments, and determining the execution form of the sub-service to be processed as a multi-department parallel cooperative service or a multi-department serial cooperative service based on the personnel processing authorities.

8. The service processing method of a knowledge-graph-based clothing customization enterprise according to claim 7, wherein after dividing the execution form of each sub-service to be processed in the service to be processed into a multi-department collaborative service or a single-department execution service according to the work content of each department in the department information corresponding to the service to be processed and the personnel processing authority in each department, the method further comprises:

if the sub-service to be processed is determined to be a multi-department parallel cooperative service or a single-department parallel service according to the work content of the clothing customization corresponding to the multiple departments and the personnel processing authority in each department, a parallel customization thread is established for the sub-service to be processed; storing the sub-services to be processed into a preset processing module so as to sequentially determine the processing form of the sub-services to be processed in the services to be processed based on the preset processing module;

if the sub-service to be processed in the service to be processed is determined to be a multi-department serial cooperative service or a single-department serial service according to the work content of the plurality of departments and the personnel processing permission of each department, acquiring the incidence relation of each work task in the sub-service to be processed according to the incidence relation of the plurality of departments;

9. The service processing method of a knowledge-graph-based clothing customization enterprise according to claim 8, wherein after determining the processing form and the processing sequence of each sub-service to be processed in the service to be processed based on the preset processing module, the method further comprises:

determining a business processing flow of the task to be processed in the clothing customizing enterprise based on the processing form and the processing sequence of each sub-business to be processed in the task to be processed so as to obtain at least one clothing production link corresponding to the business processing flow in the clothing customizing enterprise;

determining a plurality of pieces of information of personnel to be processed corresponding to the at least one clothing production link in the personnel to be selected and a plurality of business processing stages corresponding to the at least one production link according to the clothing detail design requirement information and the clothing cutting process information in the processing request information;

10. A knowledge-graph-based enterprise business processing apparatus, the apparatus comprising: a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform the method of any of claims 1-9.