Method, device and electronic device for determining work item execution object

Abstract

The present application provides a method, device and electronic device for determining the object of work item execution. The method includes: obtaining multiple target capability features corresponding to the target item; sending a first control instruction to a feature collection module, so that the feature collection module collects first information from the historical business of the office automation system according to the multiple target capability features, and the first information is used to indicate the association information of at least one target capability feature and multiple business execution objects; according to the first information and the capability model corresponding to the target item, determining the matching degree of each business execution object with the target item; when the target matching degree meets the preset conditions, determining the business execution object corresponding to the target matching degree as the target person to execute the target item. Through the present application, the problem of low efficiency of personnel selection in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the technical field of report preparation, and in particular, to a method for determining a work item execution object, an apparatus for determining a work item execution object, a computer-readable storage medium, a computer program product, and an electronic device. Background Art

[0002] Large enterprises have to prepare a large number of comprehensive reports every year. According to the requirements of the compilation guidelines, the reports are generally divided into several parts, reporting and deploying from different aspects and angles. The content is long and large in volume, involving a long time, a large space, many problems and heavy weight. The compilation of the report is led by the functional department, and the data is provided by the business according to the statistical caliber. The compilation of the entire report involves many units, departments and compilers. At present, the selection of report compilation tasks is assigned to each business unit or department according to the major chapters of the report compilation by the report leader based on his own work experience. Each unit or department then assigns the compilation content to specific business personnel for compilation. There is a large chapter involving cross-departmental business cross-compilation.

[0003] However, the current personnel assignment method requires the report leader to master the refined management of the overall business of the enterprise, and the communication cost is high, the efficiency is low, the human resources are consumed, and the business process is prone to repetition. Because the business information mastered by the compilers of the receiving units and departments does not meet the compilation requirements, the report compilation time is extended, the quality of report compilation is affected, and the enterprise management efficiency is reduced.

[0004] With the current technological revolution of artificial intelligence chatGPT and the GB or TB-level data accumulated by the development of the Internet, the learning of large models has made rapid progress, promoting the development of certain industries that replace artificial intelligence. In order to deeply tap the value of data, it is urgent to form a set of process mechanisms with stimulating driving force to promote the combination of large models and artificial explicit knowledge, deeply tap implicit knowledge, thereby iterating knowledge and experience upgrades and reducing human resource costs. Summary of the invention

[0005] The main purpose of the present application is to provide a method for determining a work item execution object, a device for determining a work item execution object, a computer-readable storage medium, a computer program product and an electronic device, so as to at least solve the problem of low efficiency of personnel assignment in the prior art.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for determining a work item execution object is provided, comprising: obtaining multiple target capability characteristics corresponding to a target item, the target item being any work item in a report, the report having corresponding multiple capability characteristics, and the multiple capability characteristics including multiple target capability characteristics; sending a first control instruction to a feature collection module so that the feature collection module collects first information from historical business of an office automation system according to the multiple target capability characteristics, the first information being used to indicate association information between at least one of the target capability characteristics and multiple business execution objects, the association representing the business execution object in the historical business and at least one of the target capability characteristics in the historical business appearing in combination; determining a matching degree between each of the business execution objects and the target item based on the first information and a capability model corresponding to the target item; and determining the business execution object corresponding to the target matching degree as a target person to execute the target item when the target matching degree meets a preset condition.

[0007] Optionally, the first information includes association frequencies between a plurality of the business execution objects and a plurality of the target capability characteristics, and determining the matching degree between each of the business execution objects and the target item according to the first information and the capability model corresponding to the target item includes: obtaining a weight coefficient of each of the target capability characteristics in the target item; and determining the matching degree between each of the business execution objects and the target item according to the formula of the association frequency, the weight coefficient and the first capability model. Determine the capability value of each of the business execution objects, where y is the capability value of each of the business execution objects, the capability value represents the degree of matching between the business execution object and the target item, i is the ranking sequence number of the target capability features in the target item, and w i The association frequency between each business execution object and the target capability feature with sorting number i, x i is the weight coefficient of the target capability feature with sorting sequence number i, and the capability model includes the first capability model.

[0008] Optionally, the first information includes target information of a plurality of the business execution objects associated with a plurality of the target capability characteristics in the historical business, and the determining the degree of matching between each of the business execution objects and the target item according to the first information and the capability model corresponding to the target item includes: obtaining a plurality of object capability characteristics of the business execution object corresponding to each of the target information; determining the matching degree between each of the business execution objects and the target item according to the formula of the plurality of object capability characteristics, the plurality of target capability characteristics and the second capability model; Determine the similarity between the capability characteristics of the multiple objects and the target capability characteristics, wherein i is the sorting sequence number of the multiple work items in the report, j is the sorting sequence number of the multiple business execution objects, and u j is the business execution object, p i is the target item, sim(u j ,p i ) is the similarity between the capability characteristics of the plurality of objects and the capability characteristics of the target, wherein the similarity represents the matching degree between the business execution object and the target item, and x i is the target capability characteristic corresponding to the target item, y j The object capability feature corresponding to the business execution object, the capability model includes the second capability model.

[0009] Optionally, the feature collection module is a software robot based on robotic process automation technology, and the feature collection module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a second control instruction to the software robot to enable the software robot to read various types of files in the historical business of the office automation system; sending a third control execution to the software robot to enable the software robot to search and determine that the data associated with the multiple target capability characteristics in the file is the first information.

[0010] Optionally, the feature acquisition module is a smart label generation model based on smart label technology, and the feature acquisition module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a fourth control instruction to the smart label generation model, so that the smart label generation model collects initial data corresponding to the multiple target capability characteristics from the historical business of the office automation system; sending a fifth control instruction to the smart label generation model, so that the smart label generation model converts the initial data into a numerical vector; sending a sixth control instruction to the smart label generation model, so that the smart label generation model imports the numerical vector into the smart label generation model to obtain a label corresponding to the numerical vector, and the label represents the first information, wherein the smart label generation model is trained by multiple sets of training data, and the multiple sets of training data include multiple historical numerical vectors and multiple historical labels.

[0011] Optionally, the determination method also includes: sending a seventh control instruction to the model training module so that the model training module obtains multiple historical numerical vectors and multiple historical labels; sending an eighth control instruction to the model training module so that the model training module trains the initial model according to the multiple historical numerical vectors, multiple historical labels and the naive Bayes algorithm to obtain the smart label generation model.

[0012] According to another aspect of the present application, a device for determining a work item execution object is provided, comprising: an acquisition module, used to acquire multiple target capability characteristics corresponding to a target item, wherein the target item is any work item in a report, and the report has multiple corresponding capability characteristics, and the multiple capability characteristics include multiple target capability characteristics; a sending module, used to send a first control instruction to a feature collection module, so that the feature collection module collects first information from historical businesses of an office automation system according to the multiple target capability characteristics, wherein the first information is used to indicate association information between at least one of the target capability characteristics and multiple business execution objects, wherein the association represents that the business execution object in the historical business appears in combination with at least one of the target capability characteristics in the historical business; a first determination module, used to determine the degree of matching between each of the business execution objects and the target item based on the first information and the capability model corresponding to the target item; and a second determination module, used to determine the business execution object corresponding to the target matching degree as a target person for executing the target item when the target matching degree meets a preset condition.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for determining the work item execution object.

[0014] According to another aspect of the present application, a computer program product is provided, including a computer program, which implements the steps of the above-mentioned method for determining a work item execution object when executed by a processor.

[0015] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for determining a work item execution object for executing the above-mentioned work item execution object.

[0016] By applying the technical solution of the present application, any work item in the report can be a target item, the report has a corresponding plurality of capability characteristics, the target item has a corresponding plurality of target capability characteristics, and the plurality of capability characteristics include a plurality of target capability characteristics. After obtaining the plurality of target capability characteristics corresponding to the target item, the present solution can first send a first control instruction to the feature acquisition module, so that the feature acquisition module can acquire first information from the historical business of the office automation system according to the plurality of target capability characteristics, wherein the first information is used to indicate the association information of at least one target capability characteristic and a plurality of business execution objects, and the association can be characterized as the business execution object in the historical business and at least one capability characteristic in the historical business appearing in combination. Then the first information can be used to determine the matching degree of each business execution object with the target item with the capability model corresponding to the target item. Afterwards, when the matching degree between any business execution object and the target item is taken as the target matching degree, if the target matching degree meets the preset conditions, the business execution object corresponding to the target matching degree can be directly determined as the target person for executing the target item. To sum up, the present application not only combines the office automation system and the feature collection module, so that the first information related to the target item in the report can be extracted from the historical business, but also matches the collected first information with the capability model corresponding to the target item, thereby achieving the purpose of effectively evaluating the degree of match between the business execution object in the first information and the target item, and accurately selecting the appropriate business execution object as the target personnel for the target item based on the degree of match, thereby improving the efficiency and quality of report preparation and solving the problem of low efficiency of personnel selection in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for determining an execution object of a work item provided in an embodiment of the present application is shown;

[0019] Figure 2 A flowchart of a method for determining a work item execution object provided in accordance with an embodiment of the present application is shown;

[0020] Figure 3 A structural block diagram of a device for determining a work item execution object provided according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] For the convenience of description, some nouns and terms involved in the embodiments of the present application are explained below:

[0025] The new enterprise think tank (NETT) with reports as business carriers is an effective way to improve the high-quality development of enterprises as a management interface. It is a new business form and new model that connects people and enterprises, and enterprises and enterprises. It is a long-term information supply and demand exchange tool that maintains interdependence and relative stability. Find the breakthrough point of NETT construction, starting from the business scenarios from report generation to report use, connect information with people, daily business, and reports through tags, and form an organic circulation model of business + information + people, so that knowledge comes from business and talents, and serves business and research.

[0026] As introduced in the background technology, the current selection of report preparation work tasks is done by business personnel who assign the report preparation chapters to various business units and departments based on their own work experience, and the leaders of each department then assign the preparation content to specific preparation personnel. However, the current personnel assignment method is time-consuming, inefficient, consumes a lot of human resources, has high human resource costs, and is prone to errors. The unit or department that receives the task may not be consistent with the preparer and the preparation content, which prolongs the report preparation time and affects the quality of report preparation. In order to solve the problem of low efficiency of personnel selection in the prior art, the embodiments of the present application provide a method for determining a work item execution object, a device for determining a work item execution object, a computer-readable storage medium, a computer program product, and an electronic device.

[0027] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for determining a task execution object according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0029] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as computer programs corresponding to the method for determining the work item execution object in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. The above network specific examples may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] In this embodiment, a method for determining the execution object of a work item running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 2 1 is a flow chart of a method for determining a work item execution object according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0032] Step S201, obtaining multiple target capability characteristics corresponding to a target item, where the target item is any work item in a report, and the report has multiple corresponding capability characteristics, and the multiple capability characteristics include multiple target capability characteristics;

[0033] Specifically, the report may include multiple work items, each of which may be considered as a collection of multiple capability characteristics, and thus the report may be considered as a collection of multiple capability characteristics corresponding to the multiple work items, so that the report has corresponding multiple capability characteristics. In the case where any one of the multiple work items is used as a target work item, the capability characteristic corresponding to the target work item is considered as a target capability characteristic, and therefore, the multiple capability characteristics corresponding to the above report include the above multiple target capability characteristics. Exemplarily, the above capability characteristics may include, but are not limited to, the name of the work item, description of the work item, requirements of the work item, capabilities required for the work item, and information on the business execution object, etc.

[0034] Step S202, sending a first control instruction to a feature collection module, so that the feature collection module collects first information from historical services of the office automation system according to a plurality of target capability features, the first information being used to indicate association information between at least one target capability feature and a plurality of service execution objects, the association representing the occurrence of a combination of a service execution object in a historical service and at least one capability feature in a historical service;

[0035] Specifically, since the first control instruction can instruct the feature collection module to collect at least one target capability feature and associated information of multiple business execution objects from historical business in the office automation system, the feature collection module can obtain the above-mentioned first information based on the above-mentioned target capability feature when receiving the first control instruction.

[0036] Step S203, determining the matching degree between each business execution object and the target item according to the first information and the capability model corresponding to the target item;

[0037] Specifically, the first information must include capability characteristics associated with the above-mentioned target item. Exemplarily, the capability characteristics may be information of the business execution object and other capability characteristics possessed by the business execution object. Other capability characteristics may be the above-mentioned capability characteristics and may include but are not limited to the name of the work item, the description of the work item, the requirements of the work item, and the capabilities required for the work item. Therefore, when matching the above-mentioned first information with the capability model corresponding to the target item, if there are fewer capability characteristics associated with the target item in the first information, it means that the business execution object in the first information has a lower matching degree with the target item. If there are more capability characteristics associated with the target item in the first information, it means that the business execution object in the first information has a higher matching degree with the target item.

[0038] Step S204: When the target matching degree meets the preset conditions, the business execution object corresponding to the target matching degree is determined as the target person for executing the target matter.

[0039] Through this embodiment, any work item in the report can be a target item, the report has a corresponding plurality of capability characteristics, the target item has a corresponding plurality of target capability characteristics, and the plurality of capability characteristics include a plurality of target capability characteristics. After obtaining the plurality of target capability characteristics corresponding to the target item, this solution can first send a first control instruction to the feature acquisition module, so that the feature acquisition module can acquire first information from the historical business of the office automation system according to the plurality of target capability characteristics, wherein the first information is used to indicate the association information of at least one target capability characteristic and a plurality of business execution objects, and the association can be characterized as the business execution object in the historical business and at least one capability characteristic in the historical business appearing in combination. Then the first information can be determined with the capability model corresponding to the target item to obtain the matching degree of each business execution object with the target item. Afterwards, when the matching degree between any business execution object and the target item is taken as the target matching degree, if the target matching degree meets the preset condition, the business execution object corresponding to the target matching degree can be directly determined as the target person for executing the target item. In summary, the present application not only combines the office automation system and the feature collection module, so that the first information related to the target item in the report can be extracted from the historical business, but also matches the collected first information with the capability model corresponding to the target item, thereby achieving the purpose of effectively evaluating the degree of match between the business execution object in the first information and the target item, and accurately selecting the appropriate business execution object as the target personnel for the target item based on the degree of match, thereby improving the efficiency and quality of report preparation and solving the problem of low efficiency of personnel selection in the prior art.

[0040] It can be known from the association frequencies of multiple business execution objects and multiple target capability characteristics that the business execution object participates in more businesses related to the target capability characteristics, and therefore can more skillfully perform the target items corresponding to the above target capability characteristics. Therefore, in some optional implementations, the first information includes the association frequencies of multiple business execution objects and multiple target capability characteristics, and the matching degree of each business execution object and the target item is determined according to the first information and the capability model corresponding to the target item, including: obtaining the weight coefficient of each target capability characteristic in the target item; according to the formula of the association frequency, the weight coefficient and the first capability model Determine the capability value of each business execution object, where y is the capability value of each business execution object, the capability value represents the degree of matching between the business execution object and the target item, i is the ranking number of multiple target capability features in the target item, and w i is the association frequency between each business execution object and the target capability feature with sorting number i, x i is the weight coefficient of the target capability feature with sorting sequence number i, and the capability model includes the first capability model.

[0041] Furthermore, in the above implementation, after obtaining the capability value of each business execution object, the business execution objects with high capability values ​​can be selected as target personnel for the target event by sorting the capability values.

[0042] In addition, the target information of each business execution object may be other capability characteristics of the business execution object. Since other capability characteristics may include but are not limited to the name of the work item, the description of the work item, the requirements of the work item and the capabilities required for the work item, etc., the degree of matching between each business execution object and the target item can be obtained by comparing the target information with the target capability characteristics of the target item. In some optional implementations, the first information includes target information of multiple business execution objects associated with multiple target capability characteristics in historical businesses, and the degree of matching between each business execution object and the target item is determined based on the first information and the capability model corresponding to the target item, including: obtaining multiple object capability characteristics of the business execution object corresponding to each target information; and according to the formula of the multiple object capability characteristics, the multiple target capability characteristics and the second capability model. Determine the similarity between the capability characteristics of multiple objects and the target capability characteristics, where i is the sorting sequence of multiple work items in the report, j is the sorting sequence of multiple business execution objects, uj is the business execution object, and p i is the target item, sim(u j ,p i ) is the similarity between the capability characteristics of multiple objects and the target capability characteristics. The similarity represents the matching degree between the business execution object and the target item. i is the target capability characteristic corresponding to the target item, y j The object capability feature corresponding to the business execution object, the capability model includes a second capability model.

[0043] Furthermore, in the above implementation, after obtaining the similarities between the capability characteristics of multiple objects and the target capability characteristics, multiple similarities corresponding to multiple business execution objects may be sorted, and then the business execution object with the highest similarity may be used as the target person for the target event.

[0044] In some other optional implementations, cosine similarity may also be used to calculate the similarity between the target event and the historical event, wherein the historical event exists in the above OA system according to the business handling process.

[0045] Exemplarily, the similarity between the target item and the historical item is calculated using cosine similarity: Among them, p i and p k are target events and historical events respectively, x i For the target item p i The corresponding target capability characteristics, xk For historical matters k The corresponding capability characteristics.

[0046] In some optional embodiments, the feature collection module is a software robot based on robotic process automation technology, and the feature collection module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a second control instruction to the software robot to enable the software robot to read various types of files in the historical business of the office automation system; sending a third control execution to the software robot to enable the software robot to search and determine that the data associated with multiple target capability characteristics in the file is the first information.

[0047] In the above implementation, since the software robot based on robotic process automation technology can obtain the required information from text or images, when the target capability characteristics corresponding to the target item are known, a second control instruction can be sent to the software robot so that the software robot can collect the above first information from the historical business of the office automation system.

[0048] In some optional embodiments, the feature collection module is a smart label generation model based on smart label technology, and the feature collection module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a fourth control instruction to the smart label generation model, so that the smart label generation model collects initial data corresponding to multiple target capability characteristics from the historical business of the office automation system; sending a fifth control instruction to the smart label generation model, so that the smart label generation model converts the initial data into a numerical vector; sending a sixth control instruction to the smart label generation model, so that the smart label generation model imports the numerical vector into the smart label generation model to obtain a label corresponding to the numerical vector, and the label represents the first information, wherein the smart label generation model is trained by multiple sets of training data, and the multiple sets of training data include multiple historical numerical vectors and multiple historical labels.

[0049] Similarly, since the smart label generation model of the new enterprise think tank smart label technology based on intelligent reporting can obtain the required information from text or images, when the target capability characteristics corresponding to the target item are known, a fourth control instruction can be sent to the smart label generation model so that the above-mentioned smart label generation model can collect the above-mentioned first information from the historical business of the office automation system.

[0050] Exemplarily, in the step where the intelligent label generation model collects initial data corresponding to multiple target capability features from the historical business of the office automation system, the intelligent label technology can first collect a large amount of data in the office automation system, including various types of data such as text and images. And by preprocessing these data, such as denoising, word segmentation and encoding, it can provide preparation for subsequent label generation. Furthermore, based on the data preprocessing, it is necessary to extract the features of the data in order to better represent the data. Among them, there are many methods for feature extraction, such as bag of words model, TF-IDF and word embedding. These methods can convert data into numerical vectors, which is convenient for subsequent model training and label generation.

[0051] Exemplarily, when the target capability characteristic is keyword A in the target matter, the initial data may be keyword A, that is, it indicates that keyword A exists in the historical business; when the target capability characteristic is keyword B in the target matter, the initial data may be keyword B, that is, it indicates that keyword B exists in the historical business. Furthermore, after the initial data is keyword A and the initial data is imported into the smart label generation model, the label generated by the smart label generation model may be the target information of the business execution object that appears in combination with the keyword A. Exemplarily, the target information may be the work number or name of the business execution object.

[0052] In order to make the above-mentioned smart label generation model more accurate, in some optional implementations, the determination method also includes: sending a seventh control instruction to the model training module so that the model training module obtains multiple historical numerical vectors and multiple historical labels; sending an eighth control instruction to the model training module so that the model training module trains the initial model according to multiple historical numerical vectors, multiple historical labels and the naive Bayes algorithm to obtain the smart label generation model.

[0053] Specifically, based on the existing data (historical numerical vectors) and labels (historical labels), the model (initial model) is trained through a machine learning algorithm (Naive Bayes algorithm). The purpose of model training is to enable the computer to learn to automatically generate labels for new data.

[0054] The theoretical basis of the above naive Bayes algorithm is Bayes' theorem, which describes the probability of an event given some known conditions. In classification problems, the naive Bayes algorithm uses Bayes' theorem to calculate the posterior probability, that is, the probability of an event occurring given the observed data. Suppose we have a classification problem in which the category set is C = {c 1 ,c 2 ,...,c k}, and we want to calculate the probability P(c|x) that x belongs to category c given the feature vector x. Bayes' theorem can be expressed as:

[0055]

[0056] in:

[0057] p(c|x) is the posterior probability, that is, the probability of category c after observing feature x.

[0058] p(x|c) is the likelihood, i.e. the probability of observing feature x under category c.

[0059] p(c) is the prior probability of class c, that is, the probability of class c before any features are observed.

[0060] p(x) is the evidence factor, which is the probability of observing feature x. It is a constant used to normalize the probabilities so that they sum to 1.

[0061] In practical applications, in order to avoid calculating a possible infinite value such as p(x), log-likelihood is usually used to avoid numerical problems, namely:

[0062] logP(c|x)=logP(x|c)+logP(c)-logP(x). Since P(x) is a constant for all categories, we can ignore it, thus simplifying it to:

[0063] logP(c|x)∝logP(x|c)+logP(c),

[0064] In the Naive Bayes algorithm, we assume that the features are independent of each other, so the likelihood probability can be decomposed into the probability product of each feature:

[0065] P(x|c)=P(x 1 |c)P(x 2 |c)...P(x n |c),

[0066] where x 1 ,x 2 ,...,x n are the components of the feature vector x. Therefore, the final classification rule (the core theoretical formula of the naive Bayes algorithm) can be expressed as:

[0067]

[0068] In practical applications, you need to estimate P(c) and P(x) based on the training data. i|c ). Generally, Naive Bayes performs well when the number of features is large because it is able to capture the independence between features.

[0069] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for determining the execution object of the work item of the present application will be described in detail below in combination with specific embodiments.

[0070] The present application embodiment also provides a kind of work item execution object determination device, it should be noted that the work item execution object determination device of the present application embodiment can be used to execute the work item execution object determination method provided by the present application embodiment. The device is used to implement the above-mentioned embodiment and preferred implementation mode, and the description has been made without further details. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0071] The following is an introduction to the device for determining the work item execution object provided in an embodiment of the present application.

[0072] Figure 3 Schematic diagram of a device for determining a work item execution object according to an embodiment of the present application. Figure 3 As shown, the device comprises:

[0073] An acquisition module 10 is used to acquire a plurality of target capability characteristics corresponding to a target item, where the target item is any work item in a report, and the report has a plurality of corresponding capability characteristics, and the plurality of capability characteristics include a plurality of target capability characteristics;

[0074] Specifically, the report may include multiple work items, each of which may be considered as a collection of multiple capability characteristics, and thus the report may be considered as a collection of multiple capability characteristics corresponding to the multiple work items, so that the report has corresponding multiple capability characteristics. In the case where any one of the multiple work items is used as a target work item, the capability characteristic corresponding to the target work item is considered as a target capability characteristic, and therefore, the multiple capability characteristics corresponding to the above report include the above multiple target capability characteristics. Exemplarily, the above capability characteristics may include, but are not limited to, the name of the work item, description of the work item, requirements of the work item, capabilities required for the work item, and information on the business execution object, etc.

[0075] The sending module 20 is used to send a first control instruction to the feature collection module, so that the feature collection module collects first information from the historical business of the office automation system according to the multiple target capability characteristics, the first information is used to indicate the association information between at least one target capability characteristic and multiple business execution objects, and the association represents that the business execution object in the historical business and at least one capability characteristic in the historical business appear in combination;

[0076] Specifically, since the first control instruction can instruct the feature collection module to collect at least one target capability feature and associated information of multiple business execution objects from historical business in the office automation system, the feature collection module can obtain the above-mentioned first information based on the above-mentioned target capability feature when receiving the first control instruction.

[0077] A first determination module 30, configured to determine the degree of matching between each business execution object and the target item according to the first information and the capability model corresponding to the target item;

[0078] Specifically, the first information must include capability characteristics associated with the above-mentioned target item. Exemplarily, the capability characteristics may be information of the business execution object and other capability characteristics possessed by the business execution object. Other capability characteristics may be the above-mentioned capability characteristics and may include but are not limited to the name of the work item, the description of the work item, the requirements of the work item, and the capabilities required for the work item. Therefore, when matching the above-mentioned first information with the capability model corresponding to the target item, if there are fewer capability characteristics associated with the target item in the first information, it means that the business execution object in the first information has a lower matching degree with the target item. If there are more capability characteristics associated with the target item in the first information, it means that the business execution object in the first information has a higher matching degree with the target item.

[0079] The second determination module 40 is used to determine the business execution object corresponding to the target matching degree as the target person for executing the target matter when the target matching degree meets the preset conditions.

[0080] Through this embodiment, any work item in the report can be a target item, the report has a corresponding plurality of capability characteristics, the target item has a corresponding plurality of target capability characteristics, and the plurality of capability characteristics include a plurality of target capability characteristics. After obtaining the plurality of target capability characteristics corresponding to the target item, this solution can first send a first control instruction to the feature acquisition module, so that the feature acquisition module can acquire first information from the historical business of the office automation system according to the plurality of target capability characteristics, wherein the first information is used to indicate the association information of at least one target capability characteristic and a plurality of business execution objects, and the association can be characterized as the business execution object in the historical business and at least one capability characteristic in the historical business appearing in combination. Then the first information can be determined with the capability model corresponding to the target item to obtain the matching degree of each business execution object with the target item. Afterwards, when the matching degree between any business execution object and the target item is taken as the target matching degree, if the target matching degree meets the preset condition, the business execution object corresponding to the target matching degree can be directly determined as the target person for executing the target item. In summary, the present application not only combines the office automation system and the feature collection module, so that the first information related to the target item in the report can be extracted from the historical business, but also matches the collected first information with the capability model corresponding to the target item, thereby achieving the purpose of effectively evaluating the degree of match between the business execution object in the first information and the target item, and accurately selecting the appropriate business execution object as the target personnel for the target item based on the degree of match, thereby improving the efficiency and quality of report preparation and solving the problem of low efficiency of personnel selection in the prior art.

[0081] It can be known from the association frequencies of multiple business execution objects and multiple target capability characteristics that the business execution object participates in more businesses related to the target capability characteristics, and therefore can more proficiently perform the target items corresponding to the above target capability characteristics. Therefore, in some optional implementations, the first information includes the association frequencies of multiple business execution objects and multiple target capability characteristics, and the first determination module includes: a first acquisition unit, which is used to obtain a weight coefficient of each target capability characteristic in the target item; a first determination unit, which is used to determine the weight coefficient of each target capability characteristic in the target item according to the association frequency, the weight coefficient and the formula of the first capability model. Determine the capability value of each business execution object, where y is the capability value of each business execution object, the capability value represents the degree of matching between the business execution object and the target item, i is the ranking number of multiple target capability features in the target item, and w i is the association frequency between each business execution object and the target capability feature with sorting number i, x i is the weight coefficient of the target capability feature with sorting sequence number i, and the capability model includes the first capability model.

[0082] In addition, the target information of each business execution object may be other capability characteristics of the business execution object, and since other capability characteristics may include but are not limited to the name of the work item, the description of the work item, the requirements of the work item and the capabilities required for the work item, etc., the degree of matching between each business execution object and the target item can be obtained by comparing the target information with the target capability characteristics of the target item, and thus in some optional implementations, the first information includes target information of multiple business execution objects associated with multiple target capability characteristics in historical business, and the first determination module includes: a second acquisition unit, for acquiring multiple object capability characteristics of the business execution object corresponding to each target information; a second determination unit, for determining the matching degree between the target information and the target item according to the formula of the multiple object capability characteristics, the multiple target capability characteristics and the second capability model. Determine the similarity between the capability characteristics of multiple objects and the target capability characteristics, where i is the sorting sequence number of multiple work items in the report, j is the sorting sequence number of multiple business execution objects, and u j For business execution objects, p i is the target item, sim(u j ,p i ) is the similarity between the capability characteristics of multiple objects and the target capability characteristics. The similarity represents the matching degree between the business execution object and the target item. i is the target capability characteristic corresponding to the target item, y j The object capability feature corresponding to the business execution object, the capability model includes a second capability model.

[0083] In some optional embodiments, the feature collection module is a software robot based on robotic process automation technology, and the feature collection module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: a first sending unit, used to send a second control instruction to the software robot, so that the software robot reads various types of files in the historical business of the office automation system; a second sending unit, used to send a third control execution to the software robot, so that the software robot searches and determines that the data associated with multiple target capability characteristics in the file is the first information.

[0084] In the above implementation, since the software robot based on robotic process automation technology can obtain the required information from text or images, when the target capability characteristics corresponding to the target item are known, the above software robot can collect the above first information from the historical business of the office automation system.

[0085] In some optional embodiments, the feature collection module is a smart label generation model based on smart label technology, and the feature collection module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: a third sending unit, used to send a fourth control instruction to the smart label generation model, so that the smart label generation model collects initial data corresponding to multiple target capability characteristics from the historical business of the office automation system; a fourth sending unit, used to send a fifth control instruction to the smart label generation model, so that the smart label generation model converts the initial data into a numerical vector; a fifth sending unit, used to send a sixth control instruction to the smart label generation model, so that the smart label generation model imports the numerical vector into the smart label generation model to obtain a label corresponding to the numerical vector, and the label represents the first information, wherein the smart label generation model is trained by multiple sets of training data, and the multiple sets of training data include multiple historical numerical vectors and multiple historical labels.

[0086] Similarly, since the smart tag generation model based on smart tag technology can obtain the required information from text or images, when the target capability characteristics corresponding to the target item are known, the above-mentioned smart tag generation model can collect the above-mentioned first information from the historical business of the office automation system.

[0087] In order to make the above-mentioned smart label generation model more accurate, in some optional embodiments, the determination device also includes: a first processing module, used to send the seventh control instruction to the model training module, so that the model training module obtains multiple historical numerical vectors and multiple historical labels; a second processing module, used to send the eighth control instruction to the model training module, so that the model training module trains the initial model according to multiple historical numerical vectors, multiple historical labels and the naive Bayes algorithm to obtain the smart label generation model.

[0088] The device for determining the execution object of the work item includes a processor and a memory, and the acquisition module, the sending module, the first determination module, the second determination module, etc. are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement the corresponding functions. The above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0089] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of low efficiency of personnel selection in the prior art is solved by adjusting kernel parameters.

[0090] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0091] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, a device where the computer-readable storage medium is located is controlled to execute a method for determining an execution object of a work item.

[0092] Specifically, the method for determining the execution object of the work item includes:

[0093] Step S201, obtaining multiple target capability characteristics corresponding to a target item, where the target item is any work item in a report, and the report has multiple corresponding capability characteristics, and the multiple capability characteristics include multiple target capability characteristics;

[0094] Specifically, the report may include multiple work items, each of which may be considered as a collection of multiple capability characteristics, and thus the report may be considered as a collection of multiple capability characteristics corresponding to the multiple work items, so that the report has corresponding multiple capability characteristics. In the case where any one of the multiple work items is used as a target work item, the capability characteristic corresponding to the target work item is considered as a target capability characteristic, and therefore, the multiple capability characteristics corresponding to the above report include the above multiple target capability characteristics. Exemplarily, the above capability characteristics may include, but are not limited to, the name of the work item, description of the work item, requirements of the work item, capabilities required for the work item, and information on the business execution object, etc.

[0095] Step S202, sending a first control instruction to a feature collection module, so that the feature collection module collects first information from historical services of the office automation system according to a plurality of target capability features, the first information being used to indicate association information between at least one target capability feature and a plurality of service execution objects, the association representing the occurrence of a combination of a service execution object in a historical service and at least one capability feature in a historical service;

[0096] Specifically, since the first control instruction can instruct the feature collection module to collect at least one target capability feature and associated information of multiple business execution objects from historical business in the office automation system, the feature collection module can obtain the above-mentioned first information based on the above-mentioned target capability feature when receiving the first control instruction.

[0097] Step S203, determining the matching degree between each business execution object and the target item according to the first information and the capability model corresponding to the target item;

[0098] Specifically, the first information must include capability characteristics associated with the above-mentioned target item. Exemplarily, the capability characteristics may be information of the business execution object and other capability characteristics possessed by the business execution object. Other capability characteristics may be the above-mentioned capability characteristics and may include but are not limited to the name of the work item, the description of the work item, the requirements of the work item, and the capabilities required for the work item. Therefore, when matching the above-mentioned first information with the capability model corresponding to the target item, if there are fewer capability characteristics associated with the target item in the first information, it means that the business execution object in the first information has a lower matching degree with the target item. If there are more capability characteristics associated with the target item in the first information, it means that the business execution object in the first information has a higher matching degree with the target item.

[0099] Step S204: When the target matching degree meets the preset conditions, the business execution object corresponding to the target matching degree is determined as the target person for executing the target matter.

[0100] Optionally, the first information includes the association frequency between multiple business execution objects and multiple target capability characteristics, and the matching degree between each business execution object and the target item is determined according to the first information and the capability model corresponding to the target item, including: obtaining the weight coefficient of each target capability characteristic in the target item; according to the formula of the association frequency, the weight coefficient and the first capability model Determine the capability value of each business execution object, where y is the capability value of each business execution object, the capability value represents the degree of matching between the business execution object and the target item, i is the ranking number of multiple target capability features in the target item, and w i is the association frequency between each business execution object and the target capability feature with sorting number i, x i is the weight coefficient of the target capability feature with sorting sequence number i, and the capability model includes the first capability model.

[0101] Optionally, the first information includes target information of multiple business execution objects associated with multiple target capability characteristics in historical business, and the matching degree of each business execution object and the target item is determined according to the first information and the capability model corresponding to the target item, including: obtaining multiple object capability characteristics of the business execution object corresponding to each target information; according to the formula of the multiple object capability characteristics, the multiple target capability characteristics and the second capability model, Determine the similarity between the capability characteristics of multiple objects and the target capability characteristics, where i is the sorting sequence number of multiple work items in the report, j is the sorting sequence number of multiple business execution objects, and u j For business execution objects, p i is the target item, sim(u j ,p i) is the similarity between the capability characteristics of multiple objects and the target capability characteristics. The similarity represents the matching degree between the business execution object and the target item. i is the target capability characteristic corresponding to the target item, y j The object capability feature corresponding to the business execution object, the capability model includes a second capability model.

[0102] Optionally, the feature collection module is a software robot based on robotic process automation technology, and the feature collection module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a second control instruction to the software robot to enable the software robot to read various types of files in the historical business of the office automation system; sending a third control execution to the software robot to enable the software robot to search and determine that the data associated with multiple target capability characteristics in the file is the first information.

[0103] Optionally, the feature acquisition module is a smart label generation model based on smart label technology, and the feature acquisition module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a fourth control instruction to the smart label generation model, so that the smart label generation model collects initial data corresponding to multiple target capability characteristics from the historical business of the office automation system; sending a fifth control instruction to the smart label generation model, so that the smart label generation model converts the initial data into a numerical vector; sending a sixth control instruction to the smart label generation model, so that the smart label generation model imports the numerical vector into the smart label generation model to obtain a label corresponding to the numerical vector, and the label represents the first information, wherein the smart label generation model is trained by multiple sets of training data, and the multiple sets of training data include multiple historical numerical vectors and multiple historical labels.

[0104] Optionally, the determination method also includes: sending a seventh control instruction to the model training module so that the model training module obtains multiple historical numerical vectors and multiple historical labels; sending an eighth control instruction to the model training module so that the model training module trains the initial model according to multiple historical numerical vectors, multiple historical labels and the naive Bayes algorithm to obtain a smart label generation model.

[0105] An embodiment of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements at least the following steps when executing the program: obtaining multiple target capability features corresponding to a target item, the target item is any work item in a report, the report has multiple corresponding capability features, and the multiple capability features include multiple target capability features; sending a first control instruction to a feature acquisition module, so that the feature acquisition module acquires first information from historical business of an office automation system according to the multiple target capability features, the first information is used to indicate the association information of at least one target capability feature and multiple business execution objects, and the association represents that a business execution object in a historical business appears in combination with at least one target capability feature in a historical business; determining the matching degree of each business execution object with the target item according to the first information and the capability model corresponding to the target item; and determining the business execution object corresponding to the target matching degree as the target person for executing the target item when the target matching degree meets a preset condition. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0106] Optionally, the first information includes the association frequency between multiple business execution objects and multiple target capability characteristics, and the matching degree between each business execution object and the target item is determined according to the first information and the capability model corresponding to the target item, including: obtaining the weight coefficient of each target capability characteristic in the target item; according to the formula of the association frequency, the weight coefficient and the first capability model Determine the capability value of each business execution object, where y is the capability value of each business execution object, the capability value represents the degree of matching between the business execution object and the target item, i is the ranking number of multiple target capability features in the target item, and w i is the association frequency between each business execution object and the target capability feature with sorting number i, x i is the weight coefficient of the target capability feature with sorting sequence number i, and the capability model includes the first capability model.

[0107] Optionally, the first information includes target information of multiple business execution objects associated with multiple target capability characteristics in historical business, and the matching degree of each business execution object and the target item is determined according to the first information and the capability model corresponding to the target item, including: obtaining multiple object capability characteristics of the business execution object corresponding to each target information; according to the formula of the multiple object capability characteristics, the multiple target capability characteristics and the second capability model, Determine the similarity between the capability characteristics of multiple objects and the target capability characteristics, where i is the sorting sequence number of multiple work items in the report, j is the sorting sequence number of multiple business execution objects, and u j For business execution objects, p i is the target item, sim(u j ,pi ) is the similarity between the capability characteristics of multiple objects and the target capability characteristics. The similarity represents the matching degree between the business execution object and the target item. i is the target capability characteristic corresponding to the target item, y j The object capability feature corresponding to the business execution object, the capability model includes a second capability model.

[0108] Optionally, the feature collection module is a software robot based on robotic process automation technology, and the feature collection module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a second control instruction to the software robot to enable the software robot to read various types of files in the historical business of the office automation system; sending a third control execution to the software robot to enable the software robot to search and determine that the data associated with multiple target capability characteristics in the file is the first information.

[0109] Optionally, the feature acquisition module is a smart label generation model based on smart label technology, and the feature acquisition module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a fourth control instruction to the smart label generation model, so that the smart label generation model collects initial data corresponding to multiple target capability characteristics from the historical business of the office automation system; sending a fifth control instruction to the smart label generation model, so that the smart label generation model converts the initial data into a numerical vector; sending a sixth control instruction to the smart label generation model, so that the smart label generation model imports the numerical vector into the smart label generation model to obtain a label corresponding to the numerical vector, and the label represents the first information, wherein the smart label generation model is trained by multiple sets of training data, and the multiple sets of training data include multiple historical numerical vectors and multiple historical labels.

[0110] Optionally, the determination method also includes: sending a seventh control instruction to the model training module so that the model training module obtains multiple historical numerical vectors and multiple historical labels; sending an eighth control instruction to the model training module so that the model training module trains the initial model according to multiple historical numerical vectors, multiple historical labels and the naive Bayes algorithm to obtain a smart label generation model.

[0111] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with at least the following method steps: obtaining multiple target capability characteristics corresponding to a target item, the target item being any work item in a report, the report having corresponding multiple capability characteristics, the multiple capability characteristics including multiple target capability characteristics; sending a first control instruction to a feature acquisition module, so that the feature acquisition module acquires first information from historical business of an office automation system according to the multiple target capability characteristics, the first information being used to indicate association information of at least one target capability characteristic and multiple business execution objects, the association representing the business execution object in the historical business and at least one target capability characteristic in the historical business appearing in combination; determining the degree of match between each business execution object and the target item based on the first information and the capability model corresponding to the target item; and determining the business execution object corresponding to the target matching degree as the target person for executing the target item when the target matching degree meets a preset condition.

[0112] Optionally, the first information includes the association frequency between multiple business execution objects and multiple target capability characteristics, and the matching degree between each business execution object and the target item is determined according to the first information and the capability model corresponding to the target item, including: obtaining the weight coefficient of each target capability characteristic in the target item; according to the formula of the association frequency, the weight coefficient and the first capability model Determine the capability value of each business execution object, where y is the capability value of each business execution object, the capability value represents the degree of matching between the business execution object and the target item, i is the ranking number of multiple target capability features in the target item, and w i is the association frequency between each business execution object and the target capability feature with sorting number i, x i is the weight coefficient of the target capability feature with sorting sequence number i, and the capability model includes the first capability model.

[0113] Optionally, the first information includes target information of multiple business execution objects associated with multiple target capability characteristics in historical business, and the matching degree of each business execution object and the target item is determined according to the first information and the capability model corresponding to the target item, including: obtaining multiple object capability characteristics of the business execution object corresponding to each target information; according to the formula of the multiple object capability characteristics, the multiple target capability characteristics and the second capability model, Determine the similarity between the capability characteristics of multiple objects and the target capability characteristics, where i is the sorting sequence number of multiple work items in the report, j is the sorting sequence number of multiple business execution objects, and u j For business execution objects, p i is the target item, sim(u j ,p i) is the similarity between the capability characteristics of multiple objects and the target capability characteristics. The similarity represents the matching degree between the business execution object and the target item. i is the target capability characteristic corresponding to the target item, y j The object capability feature corresponding to the business execution object, the capability model includes a second capability model.

[0114] Optionally, the feature collection module is a software robot based on robotic process automation technology, and the feature collection module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a second control instruction to the software robot to enable the software robot to read various types of files in the historical business of the office automation system; sending a third control execution to the software robot to enable the software robot to search and determine that the data associated with multiple target capability characteristics in the file is the first information.

[0115] Optionally, the feature acquisition module is a smart label generation model based on smart label technology, and the feature acquisition module collects first information from the historical business of the office automation system according to multiple target capability characteristics, including: sending a fourth control instruction to the smart label generation model, so that the smart label generation model collects initial data corresponding to multiple target capability characteristics from the historical business of the office automation system; sending a fifth control instruction to the smart label generation model, so that the smart label generation model converts the initial data into a numerical vector; sending a sixth control instruction to the smart label generation model, so that the smart label generation model imports the numerical vector into the smart label generation model to obtain a label corresponding to the numerical vector, and the label represents the first information, wherein the smart label generation model is trained by multiple sets of training data, and the multiple sets of training data include multiple historical numerical vectors and multiple historical labels.

[0116] Optionally, the determination method also includes: sending a seventh control instruction to the model training module so that the model training module obtains multiple historical numerical vectors and multiple historical labels; sending an eighth control instruction to the model training module so that the model training module trains the initial model according to multiple historical numerical vectors, multiple historical labels and the naive Bayes algorithm to obtain a smart label generation model.

[0117] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0119] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0122] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0123] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0124] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0125] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0126] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0127] By application, any work item in the report can be a target item, the report has corresponding multiple capability characteristics, the target item has corresponding multiple target capability characteristics, and the multiple capability characteristics include multiple target capability characteristics. After obtaining multiple target capability characteristics corresponding to the target item, this solution can first send a first control instruction to the feature acquisition module, so that the feature acquisition module can collect first information from the historical business of the office automation system according to the multiple target capability characteristics, wherein the above-mentioned first information is used to indicate the association information of at least one target capability characteristic and multiple business execution objects, and the association can be characterized as the combination of the business execution object in the historical business and at least one capability characteristic in the historical business. Then, the above-mentioned first information can be determined with the capability model corresponding to the target item to obtain the matching degree of each business execution object and the target item. Afterwards, when the matching degree between any business execution object and the target item is taken as the target matching degree, if the target matching degree meets the preset conditions, the business execution object corresponding to the target matching degree can be directly determined as the target person who executes the above-mentioned target item. In summary, the present application not only combines the office automation system and the feature collection module, so that the first information related to the target item in the report can be extracted from the historical business, but also matches the collected first information with the capability model corresponding to the target item, thereby achieving the purpose of effectively evaluating the degree of match between the business execution object in the first information and the target item, and accurately selecting the appropriate business execution object as the target personnel for the target item based on the degree of match, thereby improving the efficiency and quality of report preparation and solving the problem of low efficiency of personnel selection in the prior art.

[0128] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a work item execution object, characterized in that: include: Acquire multiple target capability characteristics corresponding to a target item, the target item being any work item in a report, the report having multiple corresponding capability characteristics, the multiple capability characteristics including multiple target capability characteristics; Sending a first control instruction to a feature collection module, so that the feature collection module collects first information from historical services of the office automation system according to the plurality of target capability features, wherein the first information is used to indicate association information between at least one of the target capability features and a plurality of service execution objects, wherein the association represents that the service execution object in the historical service appears in combination with at least one of the capability features in the historical service; Determining the matching degree between each of the business execution objects and the target item according to the first information and the capability model corresponding to the target item; When the target matching degree meets the preset conditions, the business execution object corresponding to the target matching degree is determined as the target person to execute the target matter; The feature collection module is a smart label generation model based on smart label technology. The feature collection module collects first information from historical services of the office automation system according to multiple target capability features, including: Sending a fourth control instruction to the smart label generation model so that the smart label generation model collects initial data corresponding to the plurality of target capability characteristics from historical services of the office automation system; Sending a fifth control instruction to the smart label generation model so that the smart label generation model converts the initial data into a numerical vector; Send a sixth control instruction to the smart label generation model so that the smart label generation model imports the numerical vector into the smart label generation model to obtain a label corresponding to the numerical vector, and the label represents the first information, wherein the smart label generation model is trained through multiple sets of training data, and the multiple sets of training data include multiple historical numerical vectors and multiple historical labels.

2. The determination method according to claim 1, characterized in that: The first information includes association frequencies between the plurality of the business execution objects and the plurality of the target capability characteristics, and determining the matching degree between each of the business execution objects and the target item according to the first information and the capability model corresponding to the target item includes: Obtaining a weight coefficient of each target capability feature in the target item; According to the association frequency, weight coefficient and the formula of the first capability model Determine the capability value of each of the business execution objects, where y is the capability value of each of the business execution objects, the capability value represents the degree of matching between the business execution object and the target item, i is the ranking sequence number of the target capability features in the target item, and w i The association frequency between each business execution object and the target capability feature with sorting number i, x i is the weight coefficient of the target capability feature with sorting sequence number i, and the capability model includes the first capability model.

3. The determination method according to claim 1, characterized in that: The first information includes target information of a plurality of the business execution objects associated with a plurality of the target capability characteristics in the historical business, and determining the degree of matching between each of the business execution objects and the target item according to the first information and the capability model corresponding to the target item includes: Acquire multiple object capability characteristics of the business execution object corresponding to each of the target information; According to the formula of the plurality of object capability characteristics, the plurality of target capability characteristics and the second capability model Determine the similarity between the capability characteristics of the multiple objects and the target capability characteristics, wherein i is the sorting sequence number of the multiple work items in the report, j is the sorting sequence number of the multiple business execution objects, uj is the business execution object, p i is the target item, sim(uj,pi) is the similarity between the capability characteristics of the multiple objects and the target capability characteristics, and the similarity represents the matching degree between the business execution object and the target item, x i is the target capability characteristic corresponding to the target item, y j The object capability feature corresponding to the business execution object, the capability model includes the second capability model.

4. The determination method according to any one of claims 1 to 3, characterized in that: The feature collection module is a software robot based on robotic process automation technology. The feature collection module collects first information from historical business of the office automation system according to multiple target capability features, including: sending a second control instruction to the software robot so that the software robot reads various types of files in the historical business of the office automation system; A third control execution is sent to the software robot, so that the software robot searches for and determines that the data associated with the plurality of target capability characteristics in the file is the first information.

5. The determination method according to claim 1, characterized in that: The determination method further comprises: Sending a seventh control instruction to the model training module, so that the model training module obtains the plurality of historical numerical vectors and the plurality of historical labels; Send an eighth control instruction to the model training module so that the model training module trains the initial model according to the multiple historical numerical vectors, the multiple historical labels and the naive Bayes algorithm to obtain the smart label generation model.

6. A device for determining a work item execution object, characterized in that: include: An acquisition module, used for acquiring a plurality of target capability characteristics corresponding to a target item, wherein the target item is any work item in a report, and the report has a plurality of corresponding capability characteristics, and the plurality of capability characteristics include a plurality of target capability characteristics; a sending module, configured to send a first control instruction to a feature collection module, so that the feature collection module collects first information from historical services of the office automation system according to the plurality of target capability features, wherein the first information is used to indicate association information between at least one of the target capability features and a plurality of service execution objects, wherein the association represents that the service execution object in the historical service appears in combination with at least one of the target capability features in the historical service; A first determination module, configured to determine a matching degree between each of the business execution objects and the target item according to the first information and a capability model corresponding to the target item; A second determination module is used to determine the business execution object corresponding to the target matching degree as the target person who executes the target matter when the target matching degree meets the preset conditions; The feature collection module is a smart label generation model based on smart label technology. The feature collection module collects first information from historical services of the office automation system according to multiple target capability features, including: The third sending unit is used to send a fourth control instruction to the smart label generation model, so that the smart label generation model collects initial data corresponding to the multiple target capability characteristics from the historical business of the office automation system; the fourth sending unit is used to send a fifth control instruction to the smart label generation model, so that the smart label generation model converts the initial data into a numerical vector; the fifth sending unit is used to send a sixth control instruction to the smart label generation model, so that the smart label generation model imports the numerical vector into the smart label generation model to obtain a label corresponding to the numerical vector, and the label represents the first information, wherein the smart label generation model is trained by multiple sets of training data, and the multiple sets of training data include multiple historical numerical vectors and multiple historical labels.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for determining the work item execution object according to any one of claims 1 to 5.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for determining a work item execution target according to any one of claims 1 to 5 are implemented.

9. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for determining a work item execution object as described in any one of claims 1 to 5.

Images