CN116362935A - Scheduling method, device, computer equipment and medium based on event scoring - Google Patents

Abstract

The present invention relates to the field of artificial intelligence technologies, and in particular, to a scheduling method, apparatus, computer device, and medium based on event scoring. The method comprises the steps of encoding alarm information into geographic coordinates and event information, mapping the event information into an event map according to the geographic coordinates, obtaining a real-time event map, carrying out district partition processing on the real-time event map, determining a target district to which the event information belongs, obtaining personnel information of all personnel to be scheduled in the target district, inputting the event information and the personnel information into a scoring model to obtain comprehensive scores, taking the personnel to be scheduled which are furthest forward after the comprehensive scores are ordered as target personnel, disposing the event information, converting the alarm information into the geographic coordinates through the geographic codes, generating the real-time event map, carrying out partition processing on the event and the personnel, scoring the target personnel according to scoring results, determining the interference of human factors, and being capable of carrying out parallel processing on the alarm information, thereby improving the dispatching accuracy and efficiency.

Description

Scheduling method, device, computer equipment and medium based on event scoring

Technical Field

The present invention relates to the field of artificial intelligence technologies, and in particular, to a scheduling method, apparatus, computer device, and medium based on event scoring.

Background

At present, for the scheduling processing of alarm information, scheduling personnel usually perform event analysis according to the content of the alarm information, and schedule personnel to be scheduled according to the analysis result.

However, when scheduling is performed manually, the event analysis process is affected by subjective scheduling experience of a scheduler, so that the reliability of event analysis is not high, and time consumption of manual processing is long, so that the efficiency of the scheduling process is low, and when scheduling is required to be performed simultaneously for a plurality of alarm information, the efficiency of manual scheduling is further reduced, so that how to effectively improve the efficiency and accuracy of the scheduling process becomes a problem to be solved.

Disclosure of Invention

In view of the above, the embodiments of the present invention provide a scheduling method, apparatus, computer device, and medium based on event scoring, so as to solve the problem that the efficiency and accuracy of the scheduling process are low.

In a first aspect, an embodiment of the present invention provides a scheduling method based on event scoring, where the scheduling method includes:

Encoding the acquired alarm information to obtain geographic coordinates and event information, and mapping the event information into a preset event map according to the geographic coordinates to obtain a real-time event map;

partitioning the real-time event map to obtain at least one jurisdiction, determining the jurisdiction to which the event information belongs as a target jurisdiction, and obtaining personnel information of each personnel to be scheduled in the target jurisdiction;

inputting the event information into a trained event scoring model to score the event, so as to obtain an event category score and an emergency degree score;

inputting the personnel information, the geographic coordinates, the event category scores and the emergency scores of all the personnel to be scheduled into a trained personnel scoring model for personnel scoring to obtain corresponding disposal capacity scores and space-time distance scores of all the personnel to be scheduled, and carrying out weighted addition on the disposal capacity scores and the space-time distance scores to obtain weighted addition results as comprehensive scores of all the personnel to be scheduled;

and sequencing the comprehensive scores of the people to be scheduled according to the comprehensive scores of the people to be scheduled, determining the people to be scheduled with the forefront sequencing as target people, and scheduling the target people to treat the event information.

In a second aspect, an embodiment of the present invention provides a scheduling apparatus based on event scoring, where the scheduling apparatus includes:

the information coding module is used for coding the acquired alarm information to obtain geographic coordinates and event information, and mapping the event information into a preset event map according to the geographic coordinates to obtain a real-time event map;

the partition processing module is used for carrying out partition processing on the real-time event map to obtain at least one jurisdiction, determining the jurisdiction to which the event information belongs as a target jurisdiction, and obtaining personnel information of each personnel to be scheduled in the target jurisdiction;

the event scoring module is used for inputting the event information into a trained event scoring model to score the event to obtain an event category score and an emergency degree score;

the personnel scoring module is used for inputting personnel information of each personnel to be scheduled, the geographic coordinates, the event category scores and the emergency degree scores into a trained personnel scoring model to score the personnel, obtaining corresponding treatment capacity scores and space-time distance scores of the personnel to be scheduled, and carrying out weighted addition on the treatment capacity scores and the space-time distance scores to take the weighted addition result as the comprehensive scores of the personnel to be scheduled;

And the scheduling module is used for sequencing the comprehensive scores of the personnel to be scheduled according to the comprehensive scores of the personnel to be scheduled, determining the personnel to be scheduled with the highest sequencing as a target personnel, and scheduling the target personnel to treat the event information.

In a third aspect, an embodiment of the present invention provides a computer device, the computer device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor implementing the scheduling method according to the first aspect when executing the computer program.

In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the scheduling method according to the first aspect.

Compared with the prior art, the embodiment of the invention has the beneficial effects that:

encoding the acquired alarm information to obtain geographic coordinates and event information, mapping the event information to a preset event map according to the geographic coordinates to obtain a real-time event map, carrying out partition processing on the real-time event map to obtain at least one district, determining that the district to which the event information belongs is a target district, acquiring personnel information of all personnel to be scheduled in the target district, inputting the event information into a trained event scoring model to carry out event scoring to obtain event category scoring and emergency scoring, inputting personnel information, geographic coordinates, event category scoring and emergency scoring of all personnel to be scheduled into a trained personnel scoring model to carry out personnel scoring to obtain disposal capability scoring and space-time distance scoring corresponding to all personnel to be scheduled, carrying out weighted addition on the disposal capability scoring and the space-time distance scoring, taking the weighted addition result as the comprehensive scoring of all personnel to be scheduled, sequencing the comprehensive scoring of all personnel to be scheduled according to the comprehensive scoring of all personnel to be scheduled, determining that the personnel to be scheduled are target personnel before sequencing, carrying out disposal on the event information by the scheduling target personnel, carrying out geographic coding, converting the alarm information into geographic coordinates, combining the personnel to be scheduled in the real-time, and the automatic scheduling staff to realize the automatic score, and the automatic dispatching result is improved, and the accuracy is realized according to the map of the situation of the information to be scheduled, and the information is well scored and the scheduled is well-scored and well-scored.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic view of an application environment of a scheduling method based on event scoring according to a first embodiment of the present invention;

FIG. 2 is a flowchart of a scheduling method based on event scoring according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a scheduling device based on event scoring according to a second embodiment of the present invention;

fig. 4 is a schematic structural diagram of a computer device according to a third embodiment of the present invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".

Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the invention. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

The embodiment of the invention can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

It should be understood that the sequence numbers of the steps in the following embodiments do not mean the order of execution, and the execution order of the processes should be determined by the functions and the internal logic, and should not be construed as limiting the implementation process of the embodiments of the present invention.

In order to illustrate the technical scheme of the invention, the following description is made by specific examples.

The scheduling method based on event scoring provided by the embodiment of the invention can be applied to an application environment as shown in fig. 1, wherein a client communicates with a server. The client includes, but is not limited to, a palm top computer, a desktop computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud terminal device, a personal digital assistant (personal digital assistant, PDA), and other computer devices. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

The client and the server can be deployed at a dispatching place in a dispatching scene, the client can be used for carrying out post-processing on the alarm information to obtain a dispatching scheme, the server can be connected with at least one dispatching terminal, the dispatching terminal can be a telephone dispatching terminal such as a fixed telephone and a mobile terminal or an artificial dispatching terminal such as a dispatching window and personnel uploading, and the server can be used for storing the alarm information acquired from the dispatching terminal so as to facilitate the calling of the alarm information by the client.

Referring to fig. 2, a flow chart of a scheduling method based on event scoring according to an embodiment of the present invention is provided, where the scheduling method based on event scoring may be applied to a client in fig. 1, a computer device corresponding to the client is connected to a corresponding server to obtain alarm information collected by a scheduling terminal from the server, a trained event scoring model and a trained personnel scoring model are deployed in the computer device corresponding to the client, and the trained event scoring model may be used to score event information corresponding to the alarm information to determine a category and an emergency degree of the event information, and the trained personnel scoring model may be used to score an adaptation degree between a person to be scheduled and the event information. As shown in fig. 2, the event scoring based scheduling method may include the steps of:

Step S201, encoding the acquired alarm information to obtain geographic coordinates and event information, and mapping the event information to a preset event map according to the geographic coordinates to obtain a real-time event map.

The alarm information may be information containing alarm content received by the alarm terminal, the encoding process may be used to convert the alarm information into encoded information that can be identified and processed by the computer device, the geographic coordinates may be coordinate information corresponding to an alarm address in the alarm information under a preset geographic coordinate system, and the event information may be specific alarm events in the alarm information.

The preset event map may be map information of a designated area constructed based on the above-mentioned preset geographic coordinate system, the designated area may be an area in units of cities or an area in units of jurisdictions, and the real-time event map may be an event map including real-time event information.

Specifically, in general, the alarm modes of the alarm personnel may include a telephone alarm and a field alarm, the telephone alarm corresponds to a telephone dispatch terminal, the field alarm corresponds to a manual dispatch terminal, each dispatch terminal corresponds to a dispatcher, and the dispatcher only needs to conduct information guiding and record alarm information on the alarm personnel, but does not need to analyze an event, so that human participation in the dispatching process is reduced as much as possible.

When the dispatcher guides the information of the alarm personnel, the dispatcher mainly guides the alarm personnel to describe the address information, the event classification information and the emergency degree information which are relatively standard so as to ensure that the alarm information contains accurate and processable alarm content.

The preset event map may be a map of a range involved in a scheduling task, the real-time event map and the preset event map have the same size, and the pixel information at the geographic coordinates is different only, for example, in this embodiment, the pixel at the geographic coordinate position is set to a preset value in the event map, the preset value may be 255, and the preset value should be a pixel value not included in the event map, so that the geographic coordinates corresponding to the alarm information can be clearly displayed in the real-time event map.

In an embodiment, a pixel point at a geographic coordinate position is subjected to Gaussian blur processing in an event map to obtain a Gaussian hot spot corresponding to the geographic coordinate, and the event map containing the Gaussian hot spot is determined to be a real-time event map, so that a visualization effect of the real-time event map is improved.

In the real-time event map, the pixel point information at the geographic coordinates and the event information can construct an association relationship through hyperlinks so as to facilitate manual verification.

Optionally, the encoding processing is performed on the acquired alarm information, and the obtaining of the geographic coordinates and the event information includes:

inputting the alarm information into a trained voice recognition model for voice conversion text processing to obtain an alarm text, wherein the alarm text comprises an address text and an event text;

and determining the event text as event information, encoding the address text through geocoding, and determining the encoding result as a geocoordinate.

The trained voice recognition model can be used for converting voice information corresponding to the alarm information into text information, namely alarm text, the address text can refer to text representation of an alarm address, and the event text can refer to text representation of alarm content. Geocoding may refer to the process of converting an address or place name location description into a corresponding location under a preset coordinate system, which in this embodiment may be the earth coordinate system.

Specifically, in this embodiment, the alarm information is only the voice alarm information received by the telephone scheduling terminal, and since the scheduling task of the telephone scheduling terminal is processed by the scheduling personnel, the default scheduling personnel confirms the voice information corresponding to the alarm information, that is, confirms that the voice information is clear enough, the expressed alarm content is clear enough, and does not include unrecognizable accents, etc., in the actual scheduling task, the scheduling personnel can transfer the received alarm telephone content to ensure the availability of the alarm information. It should be noted that, the dispatcher can also process the alarm information in a manual input mode, and directly obtain an alarm text when the manual input mode is adopted, and the alarm text also includes an address text and an event text, so that the processing of voice conversion text is not needed.

The trained voice recognition model can adopt acoustic models such as a transducer model, an RNN model, an LSTM model and the like, the input of the trained voice recognition model can be a voice characteristic vector corresponding to voice information, the voice characteristic vector can be characteristic information obtained by processing the voice information through processes such as framing and windowing, discrete Fourier transform, mel filtering, discrete Fourier transform and the like, and the output of the trained voice recognition model can be a text vector corresponding to the voice information. It should be noted that, in order to improve the accuracy of the trained speech recognition model in the scheduling scenario, the implementer may use the historical alert speech as the training data set of the speech recognition model, so as to enhance the recognition capability of the speech recognition model for proper nouns in the scheduling scenario.

In this embodiment, the geocoding may include address text preprocessing, search matching and plotting, where the address text preprocessing may refer to performing word segmentation processing on an address text through a preset word segmentation model, the preset word segmentation model may use a word bag model, a hidden markov model, and the like, comparing preset address dictionaries of the word segmentation processing results, standardizing and structuring the word segmentation processing results by using standard addresses in the address dictionary to obtain structural address entities, performing search matching on the structural address entities in a preset address coordinate database through a search engine to obtain at least one matching result, performing scoring on each matching result by using a preset scoring rule, determining that the matching result with the highest scoring score is a geocoding result, plotting the geocoding result, that is, mapping event information to a preset event map according to geographic coordinates, and normalizing the value domain of the scoring to [0,1], if the scoring of the matching result with the highest scoring score is not 1, that is, and if the scoring result with the highest scoring score is not completely identical to the geographic coding result, performing linear correction by using an address coordinate correction algorithm.

In the embodiment, the address text is automatically encoded into the geographic coordinates by adopting the geographic encoding service deployed in the client, manual operation is not required, and the efficiency of event map updating is improved, so that the scheduling efficiency is improved.

The step of obtaining the real-time event map by mapping the event information into the preset event map according to the geographic coordinates and the event information by encoding the obtained alarm information, and the step of obtaining the real-time event map by updating the event map in real time according to the alarm information.

Step S202, partitioning the real-time event map to obtain at least one jurisdiction, determining the jurisdiction to which the event information belongs as a target jurisdiction, and obtaining personnel information of each personnel to be scheduled in the target jurisdiction.

The partition processing may be dividing the real-time event map into at least one district, the target district may be the district to which the event information belongs, the personnel to be scheduled may be personnel who do not schedule tasks at the current moment, and the personnel information may include real-time position information of the personnel, historical processing case information and the like.

Specifically, in general, the dispatching personnel do not dispatch each other between jurisdictions, that is, the dispatching personnel only dispatch in the jurisdiction to which the dispatching personnel belong, and only when an important case occurs, the dispatching personnel between jurisdictions can dispatch each other, and the definition of the important case can be set according to actual conditions.

Optionally, partitioning the real-time event map to obtain at least one jurisdiction includes:

counting all geographic coordinates within a preset time period, determining N event coordinates as a counting result, wherein N is an integer larger than zero;

clustering N event coordinates to obtain at least one clustering set;

obtaining a district division map containing at least one district, adjusting each district in the district division map according to all the cluster sets, so that all event coordinates in any cluster set belong to the same adjusted district, determining the adjusted district division map as a division result, and determining the district division in the division result as a district.

The preset time period may refer to a time period for performing event distribution analysis, the event coordinates may refer to geographic coordinates where event information exists, the clustering process may refer to dividing the event coordinates close to each other into the same cluster set, and the cluster set may refer to a result of the clustering process.

The district division map may include at least one divided district, which may refer to a district divided according to basic geographic information, for example, district division according to a street office management area.

The adjustment of the divided jurisdiction may refer to adjustment of a boundary of the divided jurisdiction, and the partition result may refer to a result after adjustment of the divided jurisdiction, where the partition result includes a plurality of jurisdictions.

Specifically, the preset time period may be determined by a historical time point and a current time point, the historical time point may be a difference between the current time point and a preset value, the preset value may be set to 15 days in the embodiment, and the preset time period may refer to a time period for performing the event distribution analysis within 15 days.

The district partition map already comprises a fixed number of multiple partition districts, for example, the fixed number K may be 5, in this embodiment, a K-means clustering algorithm is adopted to perform clustering processing to obtain K cluster sets, for any cluster set, the partition district where the cluster center of the cluster set is located is determined, the boundary of the partition district is adjusted, all event coordinates in the cluster set are within the adjusted partition district, all event coordinates in other cluster sets are not within the adjusted partition district, the adjusted K partition districts are used as partition results, and each partition district is used as a district.

In this embodiment, the preset division jurisdiction is adjusted according to the clustering result of the event coordinates, so that the adjusted jurisdiction can conform to the event distribution of the preset time period, flexibility of jurisdiction division is improved, alarm cases in the jurisdiction can be timely processed, scheduling tasks are prevented from being allocated to people to be scheduled, which are far away from the alarm information in the same preset division jurisdiction, and overall accuracy and efficiency of scheduling are improved.

The step of carrying out partition processing on the real-time event map to obtain at least one jurisdiction, determining the jurisdiction to which the event information belongs as a target jurisdiction, and obtaining personnel information of each personnel to be scheduled in the target jurisdiction, screening out the personnel to be scheduled according to the jurisdiction information, and primarily screening out the personnel with a longer distance, thereby improving the efficiency of the scheduling process.

Step S203, inputting the event information into the trained event scoring model for event scoring to obtain event category scoring and emergency scoring.

The trained event scoring model can be used for scoring event information, the input of the trained event scoring model can be event information, the output of the trained event scoring model can be event category scoring and emergency degree scoring, the event category scoring can be used for representing event categories to which the event information belongs, and the emergency degree can be used for representing scheduling processing efficiency of event information requirements.

Optionally, the trained event scoring model includes a trained encoder, a trained event class scorer, and a trained urgency scorer;

inputting the event information into a trained event scoring model for event scoring, wherein the obtaining the event category score and the emergency score comprises the following steps:

inputting the event information into a trained encoder for feature extraction to obtain event feature vectors;

and respectively inputting the event feature vectors into a trained event category scoring device and a trained emergency scoring device for scoring to obtain event category scoring and emergency scoring.

The trained encoder can be used for extracting features of event information, the input of the trained encoder can be event information, the output of the trained encoder can be event feature vectors, the event feature vectors can be used for representing features of the event information, the trained event class scorer can be used for scoring event classes to which the event feature vectors belong, the input of the trained event class scorer can be event feature vectors, the output of the trained event class scorer can be event class scoring, the trained emergency degree scorer can be used for scoring scheduling processing efficiency of the event feature vectors, the input of the trained emergency degree scorer can also be event feature vectors, and the output of the trained emergency degree scorer can be emergency degree scoring.

Specifically, the trained event category scorer is essentially a classifier, which may be implemented using a first full connection layer.

In this embodiment, the value range of the emergency degree score is a value within [0,10], the greater the emergency degree score is, the closer to 10 is, the higher the scheduling processing efficiency of the event information requirement is, the trained emergency degree score is substantially a predictor, the predictor may be implemented by using a second full connection layer, the output of the predictor may not strictly correspond to the tag data, for example, the output of the predictor may be 8.9, and at this time, the predictor may learn the auxiliary judgment information in the event information.

In one embodiment, to improve the training efficiency of the event degree scoring model, a classifier may be used as the event degree scoring model, where the output of the classifier can only agree with the tag data, i.e. take a value in the range of [9,7,5,3,1 ].

In this embodiment, the event information is processed through the parallel scoring model, so that different scoring devices pay attention to different feature information, and the accuracy of each scoring device is improved, so that the accuracy of scoring of subsequent personnel is improved, and the accuracy and efficiency of subsequent scheduling are improved.

The event information is input into the trained event scoring model for scoring the event, so that the event category scoring and the emergency degree scoring are obtained, the event information is scored, the scoring of the personnel to be scheduled and the matching degree of the event information is conveniently determined according to the event information scoring and the personnel information, the most suitable personnel to be scheduled is determined for scheduling, and the scheduling accuracy and the scheduling task processing efficiency are improved.

Step S204, personnel information, geographic coordinates, event category scores and emergency scores of all the personnel to be scheduled are input into a trained personnel scoring model to carry out personnel scoring, disposal capacity scores and space-time distance scores corresponding to all the personnel to be scheduled are obtained, weighted addition is carried out on the disposal capacity scores and the space-time distance scores, and the weighted addition result is used as the comprehensive score of all the personnel to be scheduled.

The trained personnel scoring model can be used for scoring whether personnel to be scheduled can compete with event information, input of the trained personnel scoring model can be an input vector obtained by splicing personnel information, geographic coordinates, event category scores and emergency degree scores, input of the trained personnel scoring model can be treatment capacity scores and space-time distance scores, the treatment capacity scores can be used for representing the processing capacity of the personnel to be scheduled on the event information, and the space-time distance scores can be used for representing the distance scores between the positions of the personnel to be scheduled and the geographic coordinates of the event information. The composite score may be used to characterize the degree of fit of the personnel to be scheduled and the event information.

Specifically, the processing capability score corresponds to a first weight, the spatiotemporal distance score corresponds to a second weight, the processing capability score and the spatiotemporal distance score are weighted and added according to the first weight and the second weight, in this embodiment, the first weight may be set to 0.8, the second weight may be set to 0.2, and the implementer may adjust the values of the first weight and the second weight according to the actual situation.

Optionally, the personnel information comprises historical scheduling information and location information, and the trained personnel scoring model comprises a trained treatment capacity scoring device and a trained space-time distance scoring device;

inputting personnel information, geographic coordinates, event category scores and emergency scores into a trained personnel scoring model for personnel scoring, and obtaining treatment capacity scores and space-time distance scores comprises:

inputting the historical scheduling information, event category scores and emergency scores of all the people to be scheduled into a trained treatment capacity score device for scoring to obtain treatment capacity scores corresponding to all the people to be scheduled;

and inputting the position information and the geographic coordinates of each person to be scheduled into a trained space-time distance scoring device for scoring, and obtaining the space-time distance score corresponding to each person to be scheduled.

The position information in the personnel information can be uploaded in real time by a personnel to be scheduled through a duty terminal, the historical scheduling information can comprise statistical results of the number of various types of cases which are historically processed by the personnel to be scheduled, the processing efficiency and satisfaction statistics of each type of cases can be represented by differences of average processing time of the personnel to be scheduled for the type of cases and average processing time of all personnel for the type of cases, and the satisfaction statistics can refer to results of historical performance evaluation and work satisfaction evaluation of the personnel to be scheduled, and scoring and assignment are usually carried out by the inside of a system or feedback information of alarm personnel.

Specifically, the trained processing capability scorer may be used to score the processing capability of the person to be scheduled for the event information, the input of the trained processing capability scorer may be a first person feature vector, the output of the trained processing capability scorer may be a processing capability score, the trained spatiotemporal distance scorer may be used to score a distance between the location of the person to be scheduled and the geographic coordinates of the event information, the input of the trained spatiotemporal distance scorer may be a second person feature vector, and the output of the trained spatiotemporal distance scorer may be a spatiotemporal distance score.

And splicing the historical scheduling information, the event category score and the emergency degree score to obtain first personnel sub-information, inputting the first personnel sub-information into a trained second encoder to perform feature extraction, determining that a feature extraction result is a first personnel feature vector, and using the first personnel feature vector to characterize the feature information of the first personnel sub-information.

And splicing the position information and the geographic coordinates to obtain second personnel sub-information, inputting the second personnel sub-information into a trained third encoder for feature extraction, and determining a feature extraction result as a second personnel feature vector, wherein the second personnel feature vector can be used for representing the feature information of the second personnel sub-information.

In an embodiment, the same encoder may be used to perform feature extraction on the first personnel sub-information and the second personnel sub-information, and then the personnel feature vectors obtained by the feature extraction are respectively input into the trained disposal capability scoring device and the trained space-time distance scoring device, where the first personnel sub-information and the second personnel sub-information may be the occlusion vectors of the spliced vectors obtained by splicing the personnel information, the geographic coordinates, the event class scoring and the emergency degree scoring, in the first personnel sub-information, the vector values of the position information and the geographic coordinates are set to 0, and in the second personnel sub-information, the vector values of the historical scheduling information, the event class scoring and the emergency degree scoring are set to 0.

In this embodiment, the personnel information and the event score are processed through the parallel scoring model, so that different scorers pay attention to different feature information, the accuracy of each scorer is improved, the accuracy of personnel scoring is improved, and the accuracy and the efficiency of subsequent scheduling are improved.

And the step of inputting personnel information, geographic coordinates, event category scores and emergency scores of all the personnel to be scheduled into a trained personnel scoring model to score the personnel, obtaining corresponding disposal capacity scores and space-time distance scores of all the personnel to be scheduled, carrying out weighted addition on the disposal capacity scores and the space-time distance scores, taking the weighted addition result as the comprehensive scores of all the personnel to be scheduled, scoring the adaptation degree of the personnel information and the event information, facilitating the determination of the most suitable personnel to be scheduled, improving the scheduling accuracy and the scheduling task processing efficiency.

Step S205, sorting the comprehensive scores of all the people to be scheduled according to the comprehensive scores of all the people to be scheduled, determining the people to be scheduled with the forefront sorting as target people, and disposing the event information by the target people.

The target personnel can refer to personnel performing task scheduling processing on the event information, and the task scheduling can refer to sending the event information to terminal equipment of the target personnel so as to distribute the scheduled task.

Optionally, the ranking the composite scores corresponding to all personnel information includes:

sequencing the comprehensive scores of all the personnel to be scheduled according to the descending order to obtain a personnel sequencing result;

the step of determining the personnel to be scheduled with the forefront sequencing as target personnel comprises the following steps:

and determining the personnel to be scheduled corresponding to the comprehensive score with the forefront ranking in the personnel ranking result as the target personnel.

The descending order may be the order from big to small, the personnel sorting result may be the sorting result of the comprehensive score, the sorting position may be the position of the personnel information in sorting, and the personnel sorting result may be the sorting result of the personnel to be scheduled.

In the embodiment, the sorting result of the personnel to be scheduled is determined according to the grading sorting result, so that the target personnel is determined, the processing process is simple and easy to operate, errors are not easy to occur, and the efficiency and the accuracy of the scheduling processing are improved.

Optionally, after determining that the person to be scheduled corresponding to the top-ranked composite score is the target person, the method further includes:

Mapping the event category score and the emergency score into a demand score through a preset mapping function, wherein the mapping function comprises the mapping relation between the event category score and the emergency score and the demand score;

comparing the comprehensive scores of the target personnel with the demand scores, and if the comprehensive scores of the target personnel are smaller than the demand scores, determining the first M personnel to be scheduled with the top ranking in the personnel ranking results as target personnel;

the scheduling the target personnel to process the event information comprises the following steps:

all the determined target persons are scheduled to handle the event information.

And if the comprehensive score of the target personnel is smaller than the demand score, the target personnel is not required for the event information at the moment.

Specifically, the initial value of M may be set to 2, that is, the first two people to be scheduled ordered in the personnel ordering result are selected as target personnel, at this time, the sum of the comprehensive scores of the target personnel needs to be compared with the demand score, if the sum of the comprehensive scores of the target personnel is smaller than the demand score, the value of M is increased by one, the step of determining that the first M people to be scheduled ordered in the personnel ordering result are the target personnel is performed until the sum of the comprehensive scores of the target personnel is greater than or equal to the demand score, M target personnel are obtained, and the M target personnel are scheduled to process the event information together.

According to the method and the device for scheduling the event information, the requirement score is obtained in a mapping mode, so that whether the current target personnel can meet the requirement of the event information is determined, a plurality of target personnel can be scheduled simultaneously to perform scheduling processing of the same event information, the problem that the event information cannot be effectively processed due to the fact that the target personnel are not enough is avoided, and therefore the efficiency and the accuracy of scheduling task processing are guaranteed.

According to the comprehensive scores of the people to be scheduled, the comprehensive scores of the people to be scheduled are ranked, the people to be scheduled with the highest ranking are determined to be target people, the step that the target people handle the event information is scheduled, the most suitable target people are allocated to the event information, and the event processing efficiency, namely the event scheduling accuracy rate, can be effectively improved.

According to the method, alarming information is converted into geographic coordinates through geographic coding, and staff to be scheduled in the jurisdiction are determined in combination with the jurisdiction divided according to the real-time event map, so that the events and the staff are scored, the scheduled target staff are determined according to the scoring result, automatic scheduling is achieved, interference of human factors is avoided, and under the condition of multiple alarming information, the method can be used for parallel and rapid processing, and scheduling accuracy and scheduling efficiency are improved.

Fig. 3 shows a block diagram of a scheduling device based on event scoring according to a second embodiment of the present invention, where the scheduling device based on event scoring is applied to a client, a computer device corresponding to the client is connected to a corresponding server to obtain alarm information collected by a scheduling terminal from the server, a trained event scoring model and a trained personnel scoring model are deployed in the computer device corresponding to the client, the trained event scoring model may be used to score event information corresponding to the alarm information to determine a category and an emergency degree of the event information, and the trained personnel scoring model may be used to score a degree of adaptation between personnel to be scheduled and the event information. For convenience of explanation, only portions relevant to the embodiments of the present invention are shown.

Referring to fig. 3, the event scoring-based scheduling apparatus includes:

the information encoding module 31 is configured to encode the acquired alarm information to obtain geographic coordinates and event information, and map the event information to a preset event map according to the geographic coordinates to obtain a real-time event map;

The partition processing module 32 is configured to perform partition processing on the real-time event map to obtain at least one jurisdiction, determine the jurisdiction to which the event information belongs as a target jurisdiction, and obtain personnel information of each personnel to be scheduled in the target jurisdiction;

the event scoring module 33 is configured to input the event information into a trained event scoring model for scoring the event, so as to obtain an event category score and an emergency degree score;

the personnel scoring module 34 is configured to input personnel information, geographic coordinates, event category scores and emergency scores of all the personnel to be scheduled into a trained personnel scoring model for personnel scoring, obtain disposal capacity scores and space-time distance scores corresponding to all the personnel to be scheduled, and perform weighted addition on the disposal capacity scores and the space-time distance scores, so that the weighted addition result is used as a comprehensive score of all the personnel to be scheduled;

the scheduling module 35 is configured to sort the comprehensive scores of the people to be scheduled according to the comprehensive scores of the people to be scheduled, determine the people to be scheduled with the forefront sorting as target people, and schedule the target people to handle the event information.

Optionally, the information encoding module 31 includes:

The voice recognition sub-module is used for inputting the alarm information into the trained voice recognition model to perform voice conversion text processing to obtain an alarm text, wherein the alarm text comprises an address text and an event text;

and the geographic coding sub-module is used for determining the event text as event information, coding the address text through geographic coding and determining the coding result as geographic coordinates.

Optionally, the partition processing module 32 includes:

the coordinate statistics sub-module is used for counting all geographic coordinates in a preset time period, determining N event coordinates as statistical results, wherein N is an integer greater than zero;

the coordinate clustering sub-module is used for carrying out clustering processing on the N event coordinates to obtain at least one clustering set;

the district division sub-module is used for acquiring district division graphs containing at least one division district, adjusting each division district in the district division graphs according to all clustering sets, so that all event coordinates in any clustering set belong to the same adjusted division district, determining that the adjusted district division graphs are partition results, and determining that the division district in the partition results is district.

Optionally, the trained event scoring model includes a trained encoder, a trained event class scorer, and a trained urgency scorer;

The event scoring module 33 includes:

the feature extraction sub-module is used for inputting the event information into the trained encoder to perform feature extraction to obtain event feature vectors;

and the feature scoring sub-module is used for respectively inputting the event feature vectors into the trained event category scoring device and the trained emergency scoring device for scoring to obtain event category scoring and emergency scoring.

Optionally, the personnel information comprises historical scheduling information and location information, and the trained personnel scoring model comprises a trained treatment capacity scoring device and a trained space-time distance scoring device;

the personnel scoring module 34 includes:

the first personnel evaluation sub-module is used for inputting the historical scheduling information, the event category scores and the emergency scores of all the personnel to be scheduled into the trained disposal capacity score device for scoring to obtain disposal capacity scores corresponding to all the personnel to be scheduled;

and the second personnel scoring sub-module is used for inputting the position information and the geographic coordinates of each personnel to be scheduled into the trained space-time distance scoring device for scoring to obtain the space-time distance score corresponding to each personnel to be scheduled.

Optionally, the scheduling module 35 includes:

The scoring and sorting sub-module is used for sorting the comprehensive scores of all the personnel to be scheduled according to the descending order to obtain personnel sorting results;

and the personnel determination submodule is used for determining personnel to be scheduled corresponding to the comprehensive score with the forefront ranking in the personnel ranking result as target personnel.

Optionally, the scheduling module 35 further includes:

the scoring mapping sub-module is used for mapping the event category score and the emergency score into the demand score through a preset mapping function, and the mapping function comprises the event category score and the mapping relation between the emergency score and the demand score;

the score comparison sub-module is used for comparing the comprehensive scores of the target personnel with the demand scores, and if the comprehensive scores of the target personnel are smaller than the demand scores, the first M to-be-scheduled personnel with the forefront sequencing in the personnel sequencing result are determined to be the target personnel, and M is an integer larger than one;

and the overall scheduling sub-module is used for scheduling all the determined target personnel to treat the event information.

It should be noted that, because the content of information interaction and execution process between the modules and the sub-modules is based on the same concept as the method embodiment of the present invention, specific functions and technical effects thereof may be found in the method embodiment section, and details are not repeated here.

Fig. 4 is a schematic structural diagram of a computer device according to a third embodiment of the present invention. As shown in fig. 4, the computer device of this embodiment includes: at least one processor (only one shown in fig. 4), a memory, and a computer program stored in the memory and executable on the at least one processor, the processor executing the computer program to perform the steps of any of the various event scoring based scheduling method embodiments described above.

The computer device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that fig. 4 is merely an example of a computer device and is not intended to limit the computer device, and that a computer device may include more or fewer components than shown, or may combine certain components, or different components, such as may also include a network interface, a display screen, an input device, and the like.

The processor may be a CPU, but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory includes a readable storage medium, an internal memory, etc., where the internal memory may be the memory of the computer device, the internal memory providing an environment for the execution of an operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments may be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. that are provided on the computer device. Further, the memory may also include both internal storage units and external storage devices of the computer device. The memory is used to store an operating system, application programs, boot loader (BootLoader), data, and other programs such as program codes of computer programs, and the like. The memory may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working process of the units and modules in the above device may refer to the corresponding process in the foregoing method embodiment, which is not described herein again. The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above-described embodiment, and may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiment described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code, a recording medium, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.

The present invention may also be implemented as a computer program product for implementing all or part of the steps of the method embodiments described above, when the computer program product is run on a computer device, causing the computer device to execute the steps of the method embodiments described above.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided by the present invention, it should be understood that the disclosed apparatus/computer device and method may be implemented in other manners. For example, the apparatus/computer device embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims (10)

1. A scheduling method based on event scoring, the scheduling method comprising:

encoding the acquired alarm information to obtain geographic coordinates and event information, and mapping the event information into a preset event map according to the geographic coordinates to obtain a real-time event map;

Partitioning the real-time event map to obtain at least one jurisdiction, determining the jurisdiction to which the event information belongs as a target jurisdiction, and obtaining personnel information of each personnel to be scheduled in the target jurisdiction;

inputting the event information into a trained event scoring model to score the event, so as to obtain an event category score and an emergency degree score;

inputting the personnel information, the geographic coordinates, the event category scores and the emergency scores of all the personnel to be scheduled into a trained personnel scoring model for personnel scoring to obtain corresponding disposal capacity scores and space-time distance scores of all the personnel to be scheduled, and carrying out weighted addition on the disposal capacity scores and the space-time distance scores to obtain weighted addition results as comprehensive scores of all the personnel to be scheduled;

and sequencing the comprehensive scores of the people to be scheduled according to the comprehensive scores of the people to be scheduled, determining the people to be scheduled with the forefront sequencing as target people, and scheduling the target people to treat the event information.

2. The scheduling method according to claim 1, wherein the encoding the acquired alarm information to obtain the geographic coordinates and the event information includes:

Inputting the alarm information into a trained voice recognition model for voice conversion text processing to obtain an alarm text, wherein the alarm text comprises an address text and an event text;

and determining the event text as the event information, encoding the address text through geocoding, and determining the encoding result as the geocoordinates.

3. The scheduling method of claim 1, wherein partitioning the real-time event map to obtain at least one jurisdiction comprises:

counting all geographic coordinates within a preset time period, determining N event coordinates as a counting result, wherein N is an integer larger than zero;

clustering the N event coordinates to obtain at least one clustering set;

obtaining a district division map containing at least one district division, adjusting each district division map in the district division map according to all cluster sets, so that all event coordinates in any cluster set belong to the same adjusted district division map, determining the adjusted district division map as a district division result, and determining the district division map in the district division result as a district division result.

4. The scheduling method of claim 1, wherein the trained event scoring model comprises a trained encoder, a trained event class scorer, and a trained urgency scorer;

Inputting the event information into a trained event scoring model for event scoring, and obtaining an event category score and an emergency degree score comprises the following steps:

inputting the event information into the trained encoder for feature extraction to obtain event feature vectors;

and respectively inputting the event feature vector into the trained event category scoring device and the trained emergency scoring device to score so as to obtain the event category score and the emergency score.

5. The scheduling method of claim 1, wherein the personnel information comprises historical scheduling information and location information, and the trained personnel scoring model comprises a trained treatment ability scorer and a trained spatiotemporal distance scorer;

inputting the personnel information, the geographic coordinates, the event category scores and the emergency scores of the personnel to be scheduled into a trained personnel scoring model for personnel scoring, and obtaining the corresponding disposal capacity scores and space-time distance scores of the personnel to be scheduled comprises the following steps:

inputting the historical scheduling information, the event category scores and the emergency scores of the personnel to be scheduled into the trained treatment capacity score device for scoring to obtain the treatment capacity scores corresponding to the personnel to be scheduled;

And inputting the position information and the geographic coordinates of each person to be scheduled into the trained space-time distance scoring device for scoring to obtain space-time distance scores corresponding to each person to be scheduled.

6. The scheduling method according to any one of claims 1 to 5, wherein the ranking the composite scores of the individual people to be scheduled according to the composite scores of the individual people to be scheduled comprises:

sequencing the comprehensive scores of all the personnel to be scheduled according to the descending order to obtain a personnel sequencing result;

the step of determining the personnel to be scheduled with the forefront sequencing as target personnel comprises the following steps:

and determining the personnel to be scheduled corresponding to the comprehensive score with the forefront ranking in the personnel ranking result as the target personnel.

7. The scheduling method according to claim 6, further comprising, after the determining that the person to be scheduled corresponding to the top-ranked composite score is the target person:

mapping the event category score and the emergency score into a demand score through a preset mapping function, wherein the mapping function comprises the event category score and a mapping relation between the emergency score and the demand score;

Comparing the comprehensive score of the target personnel with the demand score, if the comprehensive score of the target personnel is smaller than the demand score, determining the first M personnel to be scheduled, which are ranked forefront, in the personnel ranking result as the target personnel, wherein M is an integer larger than one;

the scheduling the target person to handle the event information includes:

and scheduling all the determined target personnel to treat the event information.

8. A scheduling apparatus based on event scoring, the scheduling apparatus comprising:

the information coding module is used for coding the acquired alarm information to obtain geographic coordinates and event information, and mapping the event information into a preset event map according to the geographic coordinates to obtain a real-time event map;

the partition processing module is used for carrying out partition processing on the real-time event map to obtain at least one jurisdiction, determining the jurisdiction to which the event information belongs as a target jurisdiction, and obtaining personnel information of each personnel to be scheduled in the target jurisdiction;

the event scoring module is used for inputting the event information into a trained event scoring model to score the event to obtain an event category score and an emergency degree score;

The personnel scoring module is used for inputting personnel information of each personnel to be scheduled, the geographic coordinates, the event category scores and the emergency degree scores into a trained personnel scoring model to score the personnel, obtaining corresponding treatment capacity scores and space-time distance scores of the personnel to be scheduled, and carrying out weighted addition on the treatment capacity scores and the space-time distance scores to take the weighted addition result as the comprehensive scores of the personnel to be scheduled;

and the scheduling module is used for sequencing the comprehensive scores of the personnel to be scheduled according to the comprehensive scores of the personnel to be scheduled, determining the personnel to be scheduled with the forefront sequencing as target personnel, and scheduling the target personnel to treat the event information.

9. A computer device, characterized in that it comprises a processor, a memory and a computer program stored in the memory and executable on the processor, which processor implements the scheduling method according to any one of claims 1 to 7 when executing the computer program.

10. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the scheduling method according to any one of claims 1 to 7.

Images