WO2024032652A1 - Task assistance method and apparatus, electronic device, and computer readable storage medium - Google Patents

Abstract

A task assistance method and apparatus, an electronic device, and a computer readable storage medium. The task assistance method comprises: obtaining source information used for creating training content; generating target training content for execution personnel according to the source information; outputting the target training content to the execution personnel; in response to a training input of the execution personnel to the training content, comparing the training input with a preset judgment criterion; and on the basis of a comparison result, outputting feedback information of the training input to the execution personnel.

Description

A task assistance method, device, electronic equipment and computer-readable storage medium

This disclosure requires the priority of the Chinese patent application submitted to the China Patent Office on August 10, 2022, with the application number 202210957951.2, and the invention name is "a task assistance method, device, electronic equipment and storage medium", and its entire content is approved by This reference is incorporated into this disclosure.

Technical field

The present disclosure relates to the field of artificial intelligence technology, and in particular, to a task assistance method, device, electronic equipment and computer-readable storage medium.

Background technique

With breakthroughs in computing processing power, big data technology, and advances in artificial intelligence deep learning algorithms, artificial intelligence robots have become one of the hot fields, with increasing attention.

Sales means interacting with customers through communication and dialogue to achieve the goal of selling products and services. The quality of communication directly determines whether the goal can be achieved.

How to apply artificial intelligence technology to the task process and improve the efficiency of task completion is an urgent technical issue that needs to be solved.

Contents of the invention

In view of this, embodiments of the present disclosure provide a task assistance method, device, electronic device, and computer-readable storage medium, which are beneficial to improving task completion efficiency.

In a first aspect, embodiments of the present disclosure provide a task assistance method, applied to electronic devices. The method includes: obtaining source information for creating training content; the source information includes description information of an executive and the executive target task information; generate target training content for the target task for the execution personnel according to the obtained source information; output the target training content to the execution personnel according to the preset training rules; respond to the The executor compares the training input of the training content with a preset evaluation standard; based on the comparison result, outputs feedback information of the training input to the executor.

In a second aspect, embodiments of the present disclosure also provide a task assistance device for use in electronic equipment. The device includes: a courseware generation robot module configured to obtain source information for creating training content. According to the obtained source information, information to generate target training content for the target task for the executor; the source information includes description information of the executor and target task information of the executor; a sparring robot module configured to train according to a preset rules, output the target training content to the execution personnel; in response to the training input of the training content by the execution personnel, compare the training input with the preset evaluation criteria; based on the result of the comparison, The executive outputs feedback information of the training input.

In a third aspect, embodiments of the present disclosure also provide an electronic device. The electronic device includes: a casing, a processor, a memory, a circuit board, and a power circuit, wherein the circuit board is placed inside a space enclosed by the casing, and the processing The processor and memory are arranged on the circuit board; the power circuit is used to supply power to each circuit or device of the above-mentioned electronic equipment; the memory is used to store executable program code; the processor runs the program by reading the executable program code stored in the memory. The program corresponding to the executable program code is used to execute the task assistance method described in any of the aforementioned implementation methods.

In a fourth aspect, embodiments of the present disclosure also provide a computer-readable storage medium that stores one or more programs, and the one or more programs can be executed by one or more processors, To implement the task assistance method described in any of the aforementioned implementation modes.

The task assistance method, device, electronic device and computer-readable storage medium provided by the embodiments of the present disclosure can obtain the executor's According to the description information and the target task information of the executive, target training content for the target task is generated for the executive based on the description information and the target task information; according to the preset training rules, the target training content is generated for all The execution personnel output the target training content; in response to the execution personnel's training input to the training content, compare the training input with the preset evaluation criteria; based on the result of the comparison, provide the training content to the execution personnel The feedback information of the training input is output, so as to provide targeted training content for the executors. It can enable executors to quickly improve their ability to perform target tasks, thereby helping to improve task completion efficiency.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the drawings needed to be used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings in the following description are only for the purpose of describing the embodiments or related technologies. For some disclosed embodiments, those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting creative efforts.

Figure 1 is a schematic flowchart of a task assistance method provided by an embodiment of the present disclosure;

Figure 2 is a schematic diagram of outputting question-and-answer training to executives by displaying it on the display interface;

Figure 3 is a schematic diagram of the answer feedback information displayed on the display interface after the executive checks the answer and confirms it on the interface shown in Figure 2;

Figure 4 is a schematic diagram of outputting oral answers to executives by displaying them on the display interface;

Figure 5 is a schematic diagram of a task assisting device according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

It should be understood that the described embodiments are only some, but not all, of the embodiments of the present disclosure. Based on the embodiments in this disclosure, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of this disclosure.

Figure 1 is a schematic flowchart of a task assistance method according to an embodiment of the present disclosure. The task assistance method according to this embodiment can be applied to electronic devices. The electronic devices can be personal desktop computers, laptop computers, tablet computers, smart phones or smart sales terminals. The tasks involved in the task assistance method of this embodiment can be any manual task. Taking actual scenarios as an example, the task assistance method provided by this embodiment can be applied to the whole process tasks of assisted sales of financial products of financial institutions. Among them, the financial institution can be any financial product trading institution such as a bank or a fund company. In addition, the task assistance method of this embodiment can also be applied to assisted sales of products such as industrial products or consumer products. The following takes the assisted sales of financial products of a financial institution as an example to illustrate the embodiments of the present disclosure.

Referring to Figure 1, a task assistance method according to an embodiment of the present disclosure may include steps:

S11. Obtain source information used to create training content.

The source information includes description information of the execution personnel and target task information of the execution personnel.

Executives are those who perform external sales tasks in financial institutions, such as sales managers, sales specialists, etc. in financial institutions.

Executive description information is used to qualitatively or quantitatively describe the executive's sales skills, historical sales performance and other factors. For example, it can include the appointment analysis results and capability matrix, best practice analysis results, etc. of the executives' previous appointments with customers.

The target task information may include detailed information on appointment tasks created in advance for the executive, such as task arrangements, task completion status, etc.

In addition to the above information, the source information may also include at least one of the following: customer object information, product names or product categories matching the customer object, product introduction information obtained from the knowledge graph, etc.

The source information can be pre-established or set in a database, and can be updated in real time based on the collected data.

S12. According to the obtained source information, generate target training content for the target task for the executive.

Target training content can also be called courseware content. A target training content library can be established in advance, and target training content that can be evaluated from multiple different dimensions is stored in the target training content library. Each dimension can include multiple sub-dimensions, and each sub-dimension can correspond to more specific target training content. Different target training content can have corresponding difficulty levels.

According to different source information (such as the description information of the executive and the target task information), the target training matching the executive can be extracted from the target training content library from the dimension of the description information of the executive and the dimension of the target task information. Content, that is, target training content. In other words, the embodiments of the present disclosure can automatically adapt personalized training content based on execution objects and target tasks to achieve targeted personal task training.

S13. According to the preset training rules, output the target training content to the execution personnel.

The preset training rules may include sales training types, training sequences, etc.; among which, the sales training types may include question-answer training, oral answer-based training, etc. Training sequences include training sequences for different sales training types.

For question-and-answer training, the target training content can be output to the executors through at least one of audio and video methods, or the target training content can be output to the executors through silent display on the display interface.

Figure 2 is a schematic diagram of the answer-based training output to the executive by displaying it on the display interface; Figure 3 is a schematic diagram of the answer feedback information displayed on the display interface after the executive checks the answer and confirms it on the interface shown in Figure 2.

For oral answer training, the target training content can be output to the executives through voice or audio and video.

Figure 4 is a schematic diagram of outputting spoken responses to executives by displaying them on the display interface. "I have no appointment. The money just arrived yesterday. Let me have tea." shown in Figure 4 can be output to the executive through audio, so that the executive can respond or ask.

Preset training rules can also include showing training content overviews and guidelines to executives before formal training begins.

S14. In response to the training input of the training content by the executive, compare the current training input with the preset evaluation criteria.

By comparing the current training input with the preset evaluation criteria, you can determine whether the executive's training input is correct, and you can also get a score for this training.

S15. Based on the comparison result, output the feedback information of the training input to the executive.

The feedback information may include but is not limited to at least one of the following: information on whether the training input is correct, answer marks of answer content, correct answers to wrong questions, training scores, actual improvement directions and tips, etc.

After outputting the feedback information of the training input to the execution personnel, the method further includes displaying training content completion progress information to the execution personnel.

In this embodiment, by obtaining the description information of the executor and the target task information of the executor, and based on the description information and the target task information, target training content for the target task is generated for the executor; According to the preset training rules, output the target training content to the execution personnel; in response to the execution personnel's training input of the training content, compare the training input with the preset evaluation criteria; based on the comparison As a result, the feedback information of the training input is output to the execution personnel, which facilitates the provision of target training content for the execution personnel in a targeted manner. It can enable executors to quickly improve their ability to perform target tasks, thereby helping to improve task completion efficiency.

In one embodiment, the description information may include project information to be tutored; the target task information may include content information of the target task and profile information of the target customer object.

The project information to be coached may include key information on sales training for the executives, such as communication skills, sales skills, basic knowledge of products, basic knowledge of competitive products, product configuration strategies, relevant tax knowledge, etc.

The content information of the target task may include information about the products to be sold.

The target customer's profile information may include the target customer's assets, income, family members and other information.

Wherein, generating target training content for the target task for the executive according to the source information (step S12) may include:

Based on the preset target training content generation rules and different source information (such as the project information to be coached, content information, target customer information, etc.), target training content for the target task is generated for the executive .

Preset target training content generation rules can include training content (i.e. courseware) stage guidance framework and answer time estimation rules, etc. For example, it can include what type of target training content to generate, as well as the number of trainings, training duration, waiting time for answering questions, etc. .

Based on the preset target training content generation rules and different source information, it is convenient to generate target training content for the target task for the execution personnel from multiple different dimensions.

In one embodiment, generating target training content for the execution personnel for the target task may include: generating answer-based training content for the execution personnel for the target task. The content of answer-based training can be fill-in-the-blank training questions or multiple-choice training questions, etc.

Accordingly, outputting the target training content to the executive in accordance with the preset training rules includes: outputting the answer-based training content in the form of text on the display interface, or outputting the answer-based training content in the form of voice. Training content.

The method may also include recording the answer content (including wrong answer content) input by the executive.

In another embodiment, generating target training content for the target task for the executive may include: generating oral practice training content for the target task for the executive. Oral practice training is an immersive training that can simulate real sales conversation scenarios.

Correspondingly, outputting the target training content to the execution personnel according to the preset training rules includes: outputting at least one of the question content and response content corresponding to the oral practice training content in a voice manner. .

The content of oral practice training can be that the electronic device asks questions through voice, and then the executive responds to the question orally to simulate a real sales scenario between the executive and the customer. The sparring content input by the executive can be recorded.

In one embodiment, in response to the executive's training input of the training content, comparing the current training input with the preset evaluation criteria (step S14) includes: in response to the executive's input of the training content For voice training input of training content, the voice training input is recognized as text content, and the text content is compared with preset evaluation standards.

The preset evaluation criteria can be standard answers for question-answer training content, standard speaking skills for oral practice training content, etc.

The preset evaluation criteria in the above embodiments may also be a scoring rule, through which the training input content is scored to obtain a training score.

In the process of training execution objects, embodiments of the present disclosure can also perform targeted training on execution objects in stages based on the execution stage of the target task. Specifically, in a possible embodiment, the target training content involved in the present disclosure may include training content in at least one training stage, and the training content in any one of the training stages includes at least one piece of training content. Wherein, the training stage includes at least one of the following: ice-breaking stage, chat stage, risk assessment stage, risk disclosure stage, asset allocation stage, product introduction stage, and rate structure stage. It should be understood that the training content involved in each training stage is matched. When the execution object is trained, the execution object can be trained in sequence according to the task execution order, or the execution object can also choose the tasks that interest or Conduct targeted training at weak training stages.

In addition, in order to allow the execution object to more clearly distinguish between different training stages, during the process of outputting the target training content to the execution personnel, phased prompt information is output before switching to the next target stage, so The stage prompt information is used to prompt the stage goal of the next target stage.

For example, when entering the asset allocation stage from other stages, prompt information can be output on the display interface to remind the executive that the stage goals of the asset allocation stage include: 1. Review of assets and liabilities; 2. Financial goal setting; 3. Risk assessment; 4. Asset allocation portfolio; 5. Rebalancing. The stage goals here are only exemplary and are not used to limit the implementation scope of this solution.

In addition to the prompts before the training phase, the completion prompt of the training phase can also be output. For example, when the executive completes all the training content of a certain training stage, a completion prompt can be output to prompt and encourage the executive to continue working hard to complete the training and improve the enthusiasm of the executive.

In one embodiment, after comparing the current training input with the preset evaluation criteria, the method further includes:

If the accuracy of the training input is lower than the first accuracy threshold, a new first target training content is generated for the executive; wherein the difficulty level of the first target training content is lower than the most recently output target. The difficulty level of the training content;

or,

If the current training input accuracy is higher than the second accuracy threshold, new second target training content is generated for the current executive; wherein the second accuracy threshold is higher than the first accuracy Threshold: the difficulty level of the second target training content is higher than the difficulty level of the most recently output target training content.

In this embodiment, the difficulty level of the training content can be adaptively adjusted according to the training input of the execution personnel.

In one embodiment, after outputting the feedback information of the training input to the executive, the method further includes the steps:

S16. Obtain the task process file of the executive executing the target task.

The task process files involved in the embodiments of the present disclosure may include: at least one of a task audio file and a task text file. The task audio file is collected during the execution of the target task by the executor, and the task text file can be obtained by text-processing the task audio file.

During specific implementation, the task audio file may be collected by the executor using a recording device. Therefore, it may be obtained by receiving the task audio file uploaded by the executor. For example, the executor can collect the sound of the task process through the recording device to obtain the task audio file, and then connect the recording device to the electronic device, and upload the task audio file to the electronic device, thereby obtaining the execution result of the executor. The task process file of the target task. Alternatively, task audio files can also be implemented using this electronic device. For example, in other examples, when the electronic device is carried by the executioner, the electronic device can also be directly used to collect sounds of the task process and obtain the task process file. For another example, the executor of this task coaching method (such as an application or a hardware device) can display a recording control, and the user can send recording instructions by touching or voice-activating the recording control. In this way, the executor of this task coaching method can respond to Automatically collect task audio files according to the instructions of the personnel.

It should be noted that for the collection of task audio files, the target customers need to be informed in advance and their consent must be obtained.

The task audio file obtained above is processed into text to obtain the task text file. Among them, the textual processing can include but is not limited to: text conversion of audio data; or, after text conversion of audio data, combined with semantic analysis, a task text file with smooth semantics can be obtained; or, based on any of the above solutions, Then, combined with audio sentiment analysis, the sentiment analysis results are also converted into text or text tags to form a task text file.

S17. Analyze and process the task process file and generate a task process review file.

The analysis processing may include but is not limited to at least one of semantic analysis, text analysis, audio analysis, and sentiment analysis based on artificial intelligence algorithms.

The task process review files involved in the embodiments of this disclosure include but are not limited to at least one of the following: dialogue process files, satisfaction reports, compliance reports, customer churn risk reports, competitor information, and best practice reports. Below, they are explained in sequence.

First, the dialogue process file is mainly used to describe the task execution process of the executive. The data involved includes but is not limited to at least one of the following: communication records, coaching key reports, meeting minutes, and to-do items.

Among them, the communication record includes at least one of the following: a single-segment task audio file, a task audio file corresponding to each dialogue character, a task text file corresponding to each dialogue character, a task audio file carrying an issue label, and a task text carrying an issue label. document. By splitting and analyzing the task process files, the execution object can selectively review the task completion process.

In one example, analyzing and processing the task process file and generating the task process review file may include: splitting the task audio file to obtain multiple single-segment task audio files.

In one example, analyzing and processing the task process file and generating the task process review file may include: performing speech analysis on the task audio file to distinguish different dialogue roles, and obtaining task audio files that can distinguish different dialogue roles.

In one example, analyzing and processing the task process file to generate a task process review file may include: performing voice analysis on the task audio file to distinguish different dialogue roles, and performing text conversion on the task audio file to obtain a method that can distinguish different dialogue roles. Quest text file for the dialogue character.

In another example, analyzing and processing the task process file to generate a task process review file may include: performing voice analysis on the task audio file to distinguish different dialogue roles; determining the role of each dialogue role in the task process. At least one of the cumulative voice duration and the proportion of voice duration.

In another example, analyzing and processing the task process file to generate a task process review file may include: analyzing the task audio file with topic keywords to distinguish different topics, adding labels to the audio segments of different topics, and generating Task audio files with issue labels.

In another example, analyzing and processing the task process file to generate a task process review file may include: analyzing the task audio file for issue keywords, distinguishing different issues, and generating a task text file with issue tags.

You can first perform text conversion on the task audio file to obtain the task text file, and then perform issue keyword analysis on the task text file to distinguish different issues, add corresponding issue tags to the text lines or text segments of different issues, and generate issue tags. task text file.

In one implementation, the task audio files can also be analyzed for issue keywords to distinguish different issues, and then the audio clips of different issues can be text-converted and corresponding issue tags can be added to generate tasks with issue tags. text file.

In another example, analyzing and processing the task process file to generate a task process review file may include: performing keyword analysis on the task audio file to distinguish different topics; determining the cumulative value of each topic during the task process. At least one of voice duration and voice duration ratio.

The coaching points report is mainly used to summarize the problems existing in the execution of this task, so that targeted improvements can be made in the future. Therefore, a coaching point report can include at least one coaching point. Specifically, the coaching points included in the coaching points report include at least one of the following aspects: communication skills, product description issues, and risk assessment.

For example, for a task execution process of executive A, based on the analysis of its task process file, its auxiliary information can be obtained. Guidance points report, A’s coaching points mainly involve communication skills. The specific coaching points can be: 1. The ice-breaking session lacks clear meeting guidelines; the meeting sub-topics are not clearly explained; 2. The rate discussion is still not introduced 15 minutes before the end of the meeting; 3. The description of successful cases is not vivid and does not allow customers to empathize.

For another example, for the execution of a task by executive B, based on the analysis of the task process documents, a report on the coaching points can be obtained. B’s coaching points mainly involve two aspects: risk assessment and communication skills. The specific coaching points can be: 1. The overall process of risk assessment is not smooth, and other topics are inserted; 2. The third question is not understood by the customer, so detailed examples can be provided; 3. The investment period should be confirmed one by one according to the specific financial goals.

The coaching key points report can be based on the task text file, each topic label, and coaching key points generation rules to generate a coaching key points report for the executives. Among them, the guidance point generation rules are related to multi-faceted data. In an exemplary scenario, the guidance point generation rules can be updated based on the best practice report. More details later.

Meeting minutes are mainly used to facilitate readers to quickly obtain the key points of the meeting. Meeting minutes can be obtained by analyzing text such as keywords on task text files. They mainly include: main ideas and key information. In addition, formal meeting minutes can also be automatically generated according to the preset template. In addition to the main content mentioned above, the meeting minutes also include some scene information, such as meeting date, meeting time, location, participants, topics, etc. Lift. In an exemplary embodiment, a content summary analysis of the task text file can be performed to generate meeting minutes of this task process; the meeting minutes can include the main views of the communication participants, and can also include other key information, such as Time, location and other information.

To-do items are mainly used to automatically generate to-do items, freeing the hands of executives and saving their time and energy. To-do items can be obtained based on keyword and other text analysis processing of task text files, which mainly include but are not limited to: to-do item elements and content. Among them, the content can include but is not limited to at least one of the following: time, location, Characters and goals. In an exemplary embodiment, to-do items can be analyzed on the task text file to generate to-do item information; the to-do item information includes at least one of the following information: to-do content, time, location, person, to-do item The goals to be achieved, etc.

Second, the satisfaction report involved in the embodiment of the present disclosure may include but is not limited to at least one of the following aspects: product satisfaction, service satisfaction, and organization satisfaction.

Among them, product satisfaction is used to characterize the target customer's attitude towards the product, service satisfaction is used to characterize the target customer's attitude towards the services provided by the executives, and organization satisfaction user represents the target customer's overall attitude towards the service organization, so , you can fully understand the needs of target customers through satisfaction reports to facilitate follow-up.

During specific processing, all aspects involved in the satisfaction report can be obtained based on the analysis of the task text file. Taking product satisfaction as an example, it specifically includes: product name, influencing factors and satisfaction score.

In one example, keywords can be extracted from the task text file. The keywords involve 5 related aspects such as term, risk return, underlying assets, rate structure and structural design. Each aspect has a score of 1-5 in total. Level, 5 is the most satisfactory, 1 is the least satisfied, product satisfaction = term * weight + risk return * weight + underlying assets * weight + fee structure * weight + underlying assets * weight, each aspect is taken separately The values are determined by the contents of the task text file, while the weights and specific aspects included can be specifically customized.

Input the customer object's speech segment into the pre-trained machine learning model. The machine learning model will output the probability that each item corresponding to the speech segment has a score of 1 to 5 points. The score of the item with a probability value greater than the threshold is determined as The score of the project. For example, for a speech segment, the machine learning model inputs the probability that the speech segment has a deadline of 1 point as a, the probability of a deadline of 2 points as b, the probability of a deadline of 3 points as c, and the probability of a deadline of 4 points as d. , the probability that the deadline is 5 points is e. Where e is greater than the preset threshold, then the deadline score is 5 points. The machine learning model will analyze all speech segments and finally get a score for each item. If the communication sequence is later If the analysis result of the speech segment conflicts with the previous speech segment, the analysis result of the later speech segment shall prevail. For example, if the deadline is first analyzed to be 5 points, and later the deadline is analyzed to be 3 points, then the final score of the deadline is 3 points. . According to the above weight formula, calculate the final score X of product satisfaction, and determine the level of product satisfaction based on the following table.

Wherein, the satisfaction report includes at least one of the following aspects: product satisfaction, service satisfaction, and organization satisfaction.

In one embodiment, the gap between the customer's expectation value and the experience value of the designated product can be determined; and the customer's satisfaction with the designated product is determined based on the gap.

Wherein, determining the gap between the customer's expectation value and experience value for the designated product may include: determining the gap between the customer's expectation value and experience value for the designated product on at least two evaluation factors.

Correspondingly, determining the customer's satisfaction with the designated product based on the gap includes: determining the customer's satisfaction with the designated product based on the gap and weight between the expected value and the experience value on each evaluation element. Product satisfaction.

Tables 1 and 2 show the customer satisfaction evaluation model for specified products. In this evaluation model, there are five evaluation factors that determine whether a customer configures a product. The five factors are: term, risk return, underlying assets, rate structure and structural design. The five elements are weighted according to their importance. Give each interaction a customer satisfaction rating of 1 to 5, with 5 being the most satisfactory. Calculate the gap between the expectation and experience of each element, and then multiply the gap of each element by the weight to obtain the weighted gap of each element. The areas most in need of improvement can be identified based on the weighted gap size of each element.

By adding the weighted gaps of each factor, the weighted gap of customer satisfaction for the specified product can be obtained. Combined with Table 2, based on the range of the satisfaction weighted gap, the customer's satisfaction with the specified product can be determined. Product satisfaction reports may be generated automatically and may be sent to the executive, the executive's management or management, etc.

Table I:

Table II:

The method of determining customer satisfaction with services and organizational satisfaction is similar to the method of determining customer satisfaction with specified products, so no further details will be given.

Third, in this disclosed embodiment, the compliance report is mainly for the convenience of reviewers or superior leaders, so that they can quickly know the compliance issues that existed in the meeting after the meeting, so that they can be remedied in a timely manner and further targeted measures can be carried out. Compliance education and training.

Specifically, in the embodiment of the present disclosure, compliance analysis can be performed on the task text file based on preset compliance rules, and a compliance report of the task process can be generated. Among them, the preset compliance rules need to be configured in advance. The compliance rules can be rules designed based on legal provisions, or they can be custom-designed rules based on the individual needs of the organization. The embodiment of the present disclosure has no special requirements for this. limit. Based on preset compliance rules, effective process supervision of execution personnel can be achieved and risks caused by irregular execution can be avoided.

Fourth, the embodiment of the present disclosure may further include a customer churn risk report. The customer churn risk report includes but is not limited to at least one of the following aspects: information about competitors (referred to as competing products) mentioned by executives, information about competitors mentioned by target customers, and customer sentiment analysis information. During specific implementation, on the one hand, competing product information can be extracted from the task text file (for example, searching through competing product keywords or through knowledge graphs) to obtain competing product information during the task; wherein, the competing product information can include At least one of the names of competing products and competing companies. On the other hand, the customer's emotional attitude can be analyzed on the task text file to obtain the customer's emotional state information during the task; the customer's emotional state information can be the customer's emotional state score.

Among them, the competitive object information mentioned by the executive and the competitive object information mentioned by the target customer object have different emotions and attitudes for the target customer object, but both of them can be specifically used to analyze the target customer object's relationship. The emotional attitude of the competition object can, to a certain extent, assist in judging the loss possibility and customer needs of the target customer object, and in turn, can assist the execution staff in the follow-up work.

Fifth, the embodiment of the present disclosure may further include competing object information. You can refer to the fourth point above here and will not repeat it again.

Sixth, the embodiments of the present disclosure may further include best practice analysis results. When an executive performs a task, it can be regarded as a practice. As the name suggests, best practices are cases of excellent executives performing tasks. Best practices can include at least one excellent task case, which can meet the needs of executives to learn from excellent executives or excellent task cases, and can also help improve the executive's task execution capabilities.

After any executive performs a task, the task process file will be analyzed for best practices to determine whether the task meets the requirements of best practices. Therefore, when this task meets the requirements of best practices, it can Updated best practices. In this way, at this stage, the best practice analysis results of the executive's task can be determined based on at least one content such as task text files, topic tags, and coaching point reports.

In addition, the best practice analysis results can further influence the rules for generating coaching points. When updating specifically, certain expert rules or human intervention can also be combined to make the guidance point generation rules more controllable. Through the aforementioned updates, the newly generated coaching points are closer to the ability level of executives, making the coaching points more flexible and keeping pace with the times to meet the needs of executives for continuous learning and improvement.

The above six aspects can be realized by the same module or intelligent agent (or intelligent robot).

In one example, the method further includes at least one of the following:

Based on the preset expert rules and the task process review document, determine whether this communication between the executive and the target customer is a candidate best practice communication case; if confirmation instructions from the scheduled personnel are received, Identify this communication as a best practice communication example;

Provide predetermined best practice communication case information to said executive;

Provide a coaching query human-computer interaction interface; receive keywords input by the executive through the coaching query page; use the keywords as indexes to query skills matching the keywords in a preset sales skills database Content; output the queried skill content.

In one example, the task assistance method may further include: updating the guidance point generation rules based on the best practice report.

In one example, the task assistance method may further include: when the task process review file contains competing object information, updating the competing object knowledge graph based on the competing object information; wherein, the competing object Including: at least one of institutional competition objects and product competition objects.

In one example, the task assistance method may further include: obtaining historical communication data of the target customer object, and determining the investment strategy of the target executive based on the historical communication data, where the investment strategy includes at least An investment product and the recommended ratio for each investment product. Alternatively, it can also be called an investment product portfolio. Each investment product portfolio includes at least two investment products, as well as the investment recommendation ratio of the investment products.

In one embodiment, the embodiment of the present disclosure can further update the competitive object knowledge graph based on the competitive object information collected by the execution personnel during the execution of the task. Wherein, the competition objects include: at least one of institutional competition objects and product competition objects. In this way, the competitive object knowledge map can include: product map, organization map, and product-organization hybrid map.

It should be noted that the competitive object knowledge graph can be set in advance and updated in real time based on the completion of tasks by the executors. The competitive object knowledge graph can be automatically generated entirely from the task execution process data of each executive. Alternatively, the competitive object knowledge graph can also be constructed based on manual presets, network data collection, and task execution process data of each executive. .

On the other hand, in the embodiment of the present disclosure, the information of the target customer object related to the target task can also be updated based on the competitive object knowledge graph. For example, based on the competitive object knowledge graph, the target competitive object mentioned by the target customer object in the historical communication interaction data can be obtained, thereby obtaining the relevant data of the target competitive object from the competitive object knowledge graph and using it as the target customer. The object data of the object is used to implement the aforementioned process.

In an embodiment, the method may further include: based on the task process review file, predicting the order probability of the target customer object through a preset first machine learning model; according to the target customer object Probability of order completion, predicting the achievement of the executive's goals in the first cycle (for example, within one month or two months). The achievement of the goals in the first cycle includes whether the sales target of the first cycle is achieved, the first At least one of the sales performance of the cycle; output the predicted target achievement.

In addition to displaying the achievement of forecasted performance goals for the executive in question, a comparison of the achievement of forecasted performance goals for multiple executives within the organization may also be displayed.

In an embodiment, the method may further include: tracking the target tasks of the executive to determine the customer stage in which the target customer object is located; based on the determined customer stage in which the target customer object is located , count the actual number of conversions of customer objects that the executive has entered into each customer stage in the first cycle; output the target conversion of customer objects that the executive has entered into each customer stage in the first cycle according to the predetermined presentation method quantity and actual number of conversions. In this way, by comparing the target conversion number and the actual conversion number at different stages, the conversion process of the sales conversion rate can be known.

In one example, the customer stages include a possible stage, a high potential stage, and a converted stage. Among them, the possible stage may be the initial contact stage.

An embodiment of the present disclosure also provides a task assisting device for use in electronic equipment. Refer to Figure 5. The task assisting device of this embodiment 10 may include:

The courseware generation robot module 11 is configured to obtain source information for creating training content, and generate target training content for the target task for the execution personnel according to the obtained source information; the source information includes the execution personnel The description information and the target task information of the executor;

The sparring robot module 12 is configured to output the target training content to the execution personnel according to the preset training rules; in response to the execution personnel's training input to the training content, combine the training input with the preset training content. The evaluation criteria are compared; based on the result of the comparison, feedback information of the training input is output to the execution personnel.

In this embodiment, by obtaining the description information of the executor and the target task information of the executor, and based on the description information and the target task information, target training content for the target task is generated for the executor; According to the preset training rules, output the target training content to the execution personnel; in response to the execution personnel's training input of the training content, compare the training input with the preset evaluation criteria; based on the comparison As a result, the feedback information of the training input is output to the execution personnel, which facilitates the provision of target training content for the execution personnel in a targeted manner. It can enable executors to quickly improve their ability to perform target tasks, thereby helping to improve task completion efficiency.

In one embodiment, the description information includes project information to be tutored; the target task information includes content information of the target task and profile information of the target customer object;

The courseware generation robot module 11 is configured to: based on the preset target training content generation rules, as well as the project information to be tutored, the content information, and the material information of the target customer object, generate the target tasks for the execution personnel. target training content.

In one embodiment, the courseware generation robot module 11 is configured to: generate answer-based training content for the target task for the executive; wherein the training robot module 12 is configured to at least the following: One item: Output the answer-based training content to the executive in the form of text on the display interface; output the answer-based training content in the form of voice.

In one embodiment, the courseware generation robot module 11 is configured to: generate oral practice training content for the target task for the executive; wherein the practice robot module 12 is configured as : Output at least one of the question content and the response content corresponding to the oral practice training content to the executive in a voice manner.

In one embodiment, the training robot module 12 is configured to: in response to the executive's voice training input of the training content, identify the voice training input as text content, and convert the text content into Compare to preset criteria.

In one embodiment, the target training content includes the training content of at least one training stage, and the training content of any one of the training stages includes at least one piece of training content; wherein the training stage includes at least one of the following: ice-breaking stage, Chat stage, risk assessment stage, risk disclosure stage, asset allocation stage, product introduction stage, and rate structure stage.

In one embodiment, the sparring robot module is further configured to: in the process of outputting the target training content to the execution personnel, before switching to the next target stage, output phased prompt information. The sexual prompt information is used to prompt the stage goal of the next goal stage.

In one embodiment, the courseware generation robot module 11 is further configured to: if the accuracy of the training input is lower than a first accuracy threshold, generate new first target training content for the executive; Wherein, the difficulty level of the first target training content is lower than the difficulty level of the most recently output target training content;

or,

If the accuracy of the training input is higher than the second accuracy threshold, generating new second target training content for the executive; Wherein, the second accuracy threshold is higher than the first accuracy threshold, and the difficulty level of the second target training content is higher than the difficulty level of the most recently output target training content.

In one embodiment, the task assistance device 10 further includes: a conversational intelligent robot module configured to obtain the task process file of the executive performing the target task; analyze and process the task process file, Generate task process review files. The task process file includes at least one of the following: task audio file and task text file.

In one embodiment, the conversational intelligent robot module is configured to: obtain the task audio file collected by the executor during the execution of the target task, and the task audio file is uploaded by the executor, Alternatively, the task audio file is automatically collected in response to instructions from the executive; the task audio file is processed into text to obtain the task text file.

In one embodiment, the task process review file includes at least one of the following: dialogue process file, satisfaction report, compliance report, customer churn risk report, competitor information, and best practice report; wherein, the satisfaction report The degree report includes at least one of the following aspects: product satisfaction, service satisfaction, and organizational satisfaction.

In one embodiment, the dialogue process files include at least one of the following: communication records, coaching key points reports, meeting minutes, and to-do items; the communication records include at least one of the following: single-segment task audio files, dialogue role respective The corresponding task audio files, the task text files corresponding to the dialogue characters, the task audio files carrying issue tags, and the task text files carrying issue tags.

In one embodiment, when the task process review file includes the coaching key points report, the conversational intelligent robot module is configured to: generate rules based on the task text file, each topic label, and coaching key points, as The executive generates a coaching key points report; the coaching key points included in the coaching key points report include at least one of the following aspects: communication skills, product description issues, and risk assessment.

In one embodiment, the conversational intelligent robot module is further configured to be at least one of the following:

Based on the preset expert rules and the task process review document, determine whether this communication between the executive and the target customer is a candidate best practice communication case; if confirmation instructions from the scheduled personnel are received, Identify this communication as a best practice communication example;

Provide predetermined best practice communication case information to said executive;

Provide a coaching query human-computer interaction interface; receive keywords input by the executive through the coaching query page; use the keywords as indexes to query skills matching the keywords in a preset sales skills database Content; output the queried skill content.

In one embodiment, the task assistance device further includes: a first update module configured to update the coaching point generation rules based on the best practice report.

In one embodiment, the task assistance device further includes: a second update module (which can also be called a knowledge graph robot or a knowledge graph agent) configured to detect when the task process review file contains a competing object. When receiving information, the competitive object knowledge graph is updated based on the competitive object information; wherein the competitive object includes at least one of an institutional competitive object and a product competitive object.

In one embodiment, the task assistance device further includes: an investment strategy determination module configured to obtain historical communication data of the target customer object, and determine the investment of the target executive based on the historical communication data. Strategy, the investment strategy includes at least one investment product and a recommended proportion of each investment product.

In one embodiment, the task assisting device 10 further includes: a performance prediction robot module configured to: based on the The task process review file predicts the order probability of the target customer object through the preset first machine learning model; predicts the achievement of the first cycle goal of the executive based on the order probability of the target customer object. The first cycle target achievement status includes whether at least one of the first cycle sales target and the first cycle sales performance is achieved; and the predicted target achievement status is output.

In one embodiment, the task assisting device 10 further includes: a sales funnel robot module configured to track the target tasks of the executive to determine the customer stage in which the target customer object is; based on the The determined customer stage of the target customer object is updated, and the actual number of conversions of customer objects that the executive enters into each customer stage in the first cycle is updated; and the actual conversion number of the customer object entered by the executive in the first cycle is output according to the predetermined presentation method. The target number of conversions and the actual number of conversions of customer objects entering each customer stage.

In one embodiment, in the task assisting device 10, the customer stages include a possible stage, a high potential stage and a converted stage.

Each of the above-mentioned task assistance devices 10 can correspondingly implement the above-mentioned task assistance method embodiments, and their implementation processes and technical effects are basically the same, and will not be described again here.

Referring to Figure 6, an embodiment of the present disclosure also provides an electronic device. The electronic device includes: a housing 51, a processor 52, a memory 53, a circuit board 54 and a power circuit 55, wherein the circuit board 54 is disposed in the housing 51 Inside the enclosed space, the processor 52 and the memory 53 are arranged on the circuit board 54; the power circuit 55 is used to supply power to various circuits or devices of the above-mentioned electronic equipment; the memory 53 is used to store executable program codes; the processor 52 passes Read the executable program code stored in the memory to run the program corresponding to the executable program code, which is used to implement any of the task assistance methods provided by the foregoing embodiments. Therefore, the corresponding technical effects can also be achieved. The details have been described above. Description will not be repeated here.

The above-mentioned electronic devices exist in many forms, including but not limited to:

(1) Mobile communication equipment: This type of equipment is characterized by its mobile communication function and its main goal is to provide voice and data communication. Such terminals include: smart phones (such as iPhone), multimedia phones, feature phones, etc.

(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally also has mobile Internet features. Such terminals include: PDA, MID and UMPC devices, such as iPad.

(3) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server is similar to a general computer architecture, but due to the need to provide high-reliability services, it requires less processing power and stability. , reliability, security, scalability, manageability and other aspects have higher requirements.

(4) Other electronic devices with data interaction functions.

Correspondingly, embodiments of the present disclosure also provide a computer-readable storage medium that stores one or more programs, and the one or more programs can be executed by one or more processors, In order to implement any of the task assistance methods provided by the foregoing embodiments, corresponding technical effects can also be achieved. This has been described in detail above and will not be described again here.

Embodiments of the present disclosure also provide a computer-readable storage medium that stores one or more programs, and the one or more programs can be executed by one or more processors to implement the foregoing implementation. Any task auxiliary method provided by the example can also achieve corresponding technical effects. This has been explained in detail above and will not be repeated here.

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations are mutually exclusive. any such actual relationship or sequence exists between them. Furthermore, the terms "includes,""includes," or any other variation thereof are intended to cover a non-exclusive inclusion, such that the inclusion of a A process, method, article, or device with a set of elements includes not only those elements but also other elements not expressly listed, or elements inherent to the process, method, article, or device. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of additional identical elements in a process, method, article, or apparatus that includes the stated element.

Each embodiment in this specification is described in a related manner. The same and similar parts between the various embodiments can be referred to each other. Each embodiment focuses on its differences from other embodiments.

In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For relevant details, please refer to the partial description of the method embodiment.

For the convenience of description, the above device is described by dividing its functions into various units/modules. Of course, when implementing the present disclosure, the functions of each unit/module can be implemented in the same or multiple software, the same or multiple hardware, or the same or multiple software and hardware.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. The program can be stored in a computer-readable storage medium. During execution, the process may include the processes of the embodiments of each of the above methods. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM), etc.

The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure. All are covered by the protection scope of this disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims (42)

1. A task assistance method, applied to electronic equipment, the method includes:

   Obtain source information used to create training content; the source information includes description information of the executive and target task information of the executive;

   Generate target training content for the target task for the executive according to the obtained source information;

   According to the preset training rules, output the target training content to the execution personnel;

   In response to the executive's training input on the training content, comparing the training input with a preset evaluation criterion;

   Based on the result of the comparison, feedback information of the training input is output to the executive.
2. The task assistance method according to claim 1, wherein,

   The description information includes information about the project to be tutored;

   The target task information includes the content information of the target task and the profile information of the target customer object;

   Generating target training content for the target task for the executive based on the source information includes:

   Based on the preset target training content generation rules, as well as the project information to be coached, the content information, and the profile information of the target customer object, target training content for the target task is generated for the executive.
3. The task assistance method according to claim 1, wherein generating target training content for the target task for the executive includes:

   Generate answer-based training content for the execution personnel that is specific to the target task;

   Wherein, outputting the target training content to the execution personnel according to the preset training rules includes at least one of the following:

   Output the question-and-answer training content to the executive in the form of text on the display interface;

   The question-answering training content is output in the form of voice.
4. The task assistance method according to claim 1, wherein generating target training content for the target task for the executive includes:

   Generate oral practice training content for the execution personnel for the target task;

   Wherein, the step of outputting the target training content to the execution personnel according to the preset training rules includes:

   In the form of voice, at least one of the question content and the response content corresponding to the oral practice training content is output to the executive.
5. The task assistance method according to claim 3 or 4, wherein, in response to the training input of the training content by the executive, comparing the training input with a preset evaluation standard includes:

   In response to the voice training input of the training content by the executive, the voice training input is recognized as text content, and the text content is compared with a preset evaluation standard.
6. The task assistance method according to claim 1, wherein the target training content includes training content of at least one training stage, and the training content of any one of the training stages includes at least one piece of training content;

   Wherein, the training stage includes at least one of the following: ice-breaking stage, chat stage, risk assessment stage, risk disclosure stage, asset allocation stage, product introduction stage, and rate structure stage.
7. The task assistance method according to claim 6, wherein the method further includes:

   In the process of outputting the target training content to the execution personnel, before switching to the next target stage, phase prompt information is output, and the phase prompt information is used to prompt the stage goals of the next target stage.
8. The task assistance method according to claim 1, wherein after comparing the training input with a preset criterion, the method further includes:

   If the accuracy of the training input is lower than the first accuracy threshold, a new first target training content is generated for the executive; wherein the difficulty level of the first target training content is lower than the latest output. The difficulty level of the target training content;

   or,

   If the accuracy of the training input is higher than the second accuracy threshold, new second target training content is generated for the executive; wherein the second accuracy threshold is higher than the first accuracy threshold, The difficulty level of the second target training content is higher than the difficulty level of the most recently output target training content.
9. The task assistance method according to any one of claims 1 to 8, wherein after outputting the feedback information of the training input to the executive, the method further includes:

   Obtain the task process file in which the executive performs the target task; the task process file includes: at least one of a task audio file and a task text file;

   The task process file is analyzed and processed to generate a task process review file.
10. The method according to claim 9, wherein the obtaining the task process file of the execution personnel performing the target task includes:

    Obtain the task audio file collected during the execution of the target task by the executioner. The task audio file is uploaded by the executioner, or the task audio file is generated in response to the instruction of the executioner. automatically collected;

    The task audio file is processed into text to obtain the task text file.
11. The method according to claim 9, wherein the task process review file includes at least one of the following: dialogue process files, satisfaction reports, compliance reports, customer churn risk reports, competitive object information, and best practice reports;

    Wherein, the satisfaction report includes at least one of the following aspects: product satisfaction, service satisfaction, and organizational satisfaction.
12. The method according to claim 11, wherein the dialogue process document includes at least one of the following: communication records, coaching key points reports, meeting minutes, and to-do items;

    The communication record includes at least one of the following: a single-segment task audio file, a task audio file corresponding to each dialogue character, a task text file corresponding to each dialogue character, a task audio file carrying an issue tag, and a task text carrying an issue tag. document.
13. The method according to claim 12, wherein when the task process review file includes the coaching key points report, analyzing and processing the task process file to generate a task process review file includes:

    Based on the task text file, each topic label, and the coaching point generation rules, a coaching point report is generated for the executive; the coaching points included in the coaching point report include at least one of the following aspects: communication skills, product description issues, Risk assessment.
14. The method according to any one of claims 1-8, wherein the method further includes at least one of the following:

    Based on the preset expert rules and the task process review document, determine whether this communication between the executive and the target customer is a candidate best practice communication case; if confirmation instructions from the scheduled personnel are received, Identify this communication as a best practice communication example;

    Provide predetermined best practice communication case information to said executive;

    Provide a coaching query human-computer interaction interface; receive keywords input by the executive through the coaching query page; use the keywords as indexes to query skills matching the keywords in a preset sales skills database Content; output the queried skill content.
15. The task assistance method according to claim 14, wherein the method further includes:

    Based on the best practices report, the coaching point generation rules are updated.
16. The task assistance method according to claim 11, wherein the method further includes:

    When the task process review file contains competition object information, the competition object knowledge map is updated based on the competition object information; wherein the competition object includes at least one of an organization competition object and a product competition object.
17. The task assistance method according to claim 9, wherein the method further includes:

    Obtain the historical communication data of the target customer object, and determine the investment strategy of the target executive based on the historical communication data. The investment strategy includes at least one investment product and a recommended ratio of each investment product.
18. The task assistance method according to claim 9, wherein the method further includes:

    Based on the task process review file, predict the order probability of the target customer through the preset first machine learning model;

    According to the order probability of the target customer object, predict the achievement of the first cycle goal of the executive. The achievement of the first cycle goal includes whether the sales target of the first cycle is achieved and the sales performance of the first cycle. at least one of;

    Output the predicted goal achievement.
19. The task assistance method according to any one of claims 1-18, wherein the method further includes:

    Tracking the target tasks of the executive to determine the customer stage of the target customer object;

    Based on the determined customer stage of the target customer object, update the actual conversion number of customer objects that the executive entered into each customer stage in the first cycle;

    The target conversion number and the actual conversion number of the customer objects that the executive entered into each customer stage in the first cycle are output according to a predetermined presentation method.
20. The task assisting method according to claim 19, wherein the customer stages include a possible stage, a high potential stage and a converted stage.
21. A task assistance device, applied to electronic equipment, the device includes:

    A courseware generation robot module is configured to obtain source information for creating training content, and generate target training content for the target task for the executive based on the obtained source information; the source information includes the executive's Descriptive information and target task information of said executive;

    The sparring robot module is configured to output the target training content to the executor according to the preset training rules; in response to the executor's training input of the training content, combine the training input with the preset judgment Standards are compared; based on the result of the comparison, feedback information of the training input is output to the executive.
22. The task assistance device according to claim 21, wherein the description information includes project information to be tutored; the target task information includes content information of the target task and profile information of the target customer object;

    The courseware generation robot module is configured to: based on the preset target training content generation rules, as well as the project information to be tutored, the content information, and the material information of the target customer object, generate for the execution personnel a training course for the target task. Target training content.
23. The task assisting device according to claim 21, wherein:

    The courseware generation robot module is configured to: generate answer-based training content for the execution personnel for the target task;

    Wherein, the training robot module is configured to at least one of the following: output the answer-based training content to the executive in the form of text on the display interface; output the answer-based training content in the form of voice.
24. A task assistance device according to claim 21,

    The courseware generation robot module is configured to: generate oral practice training content for the target task for the execution personnel;

    Wherein, the sparring robot module is configured to output at least one of question content and response content corresponding to the oral sparring training content to the executive in a voice manner.
25. The task assistance device according to claim 23 or 24, wherein the sparring robot module is configured to:

    In response to the voice training input of the training content by the executive, the voice training input is recognized as text content, and the text content is compared with a preset evaluation standard.
26. The task assistance device according to claim 21, wherein the target training content includes training content of at least one training stage, and the training content of any one of the training stages includes at least one piece of training content;

    Wherein, the training stage includes at least one of the following: ice-breaking stage, chat stage, risk assessment stage, risk disclosure stage, asset allocation stage, product introduction stage, and rate structure stage.
27. The task assistance device according to claim 26, wherein the sparring robot module is further configured to:

    In the process of outputting the target training content to the execution personnel, before switching to the next target stage, phase prompt information is output, and the phase prompt information is used to prompt the stage goals of the next target stage.
28. The task assistance device according to claim 21, wherein the courseware generation robot module is further configured to:

    If the accuracy of the training input is lower than the first accuracy threshold, a new first target training content is generated for the executive; wherein the difficulty level of the first target training content is lower than the latest output. The difficulty level of the target training content;

    or,

    If the accuracy of the training input is higher than the second accuracy threshold, new second target training content is generated for the executive; wherein the second accuracy threshold is higher than the first accuracy threshold, The difficulty level of the new target training content is higher than the difficulty level of the most recently output target training content.
29. The task assisting device according to any one of claims 21-28, further comprising:

    The dialogue intelligent robot module is configured to obtain the task process file of the executioner performing the target task; analyze and process the task process file to generate a task process review file; the task process file includes: task audio file , at least one of the task text files.
30. The task assistance device according to claim 29, wherein the conversational intelligent robot module is configured to:

    Obtain the task audio file collected during the execution of the target task by the executioner. The task audio file is uploaded by the executioner, or the task audio file is generated in response to the instruction of the executioner. automatically collected;

    The task audio file is processed into text to obtain the task text file.
31. The task assistance device according to claim 29, wherein the task process review file includes at least one of the following: dialogue process file, satisfaction report, compliance report, customer churn risk report, competitive object information, best practice Report;

    Wherein, the satisfaction report includes at least one of the following aspects: product satisfaction, service satisfaction, and organizational satisfaction.
32. The task assistance device according to claim 31, wherein the conversation process file includes at least one of the following: communication records, coaching key points reports, meeting minutes, and to-do items;

    The communication record includes at least one of the following: a single-segment task audio file, a task audio file corresponding to each dialogue character, a task text file corresponding to each dialogue character, a task audio file carrying an issue tag, and a task text carrying an issue tag. document.
33. The task assistance device according to claim 32, wherein when the task process review file includes the coaching key points report, the conversational intelligent robot module is configured to:

    Based on the task text file, each topic label, and the coaching point generation rules, a coaching point report is generated for the executive; the coaching points included in the coaching point report include at least one of the following aspects: communication skills, product description issues, Risk assessment.
34. The task assistance device according to claim 32, wherein the conversational intelligent robot module is further configured to be at least one of the following:

    Based on the preset expert rules and the task process review document, determine whether this communication between the executive and the target customer is a candidate best practice communication case; if confirmation instructions from the scheduled personnel are received, Identify this communication as a best practice communication example;

    Provide predetermined best practice communication case information to said executive;

    Provide a coaching query human-computer interaction interface; receive keywords input by the executive through the coaching query page; use the keywords as indexes to query skills matching the keywords in a preset sales skills database Content; output the queried skill content.
35. The task assistance device according to claim 34, further comprising: a first update module configured to update coaching point generation rules based on the best practice report.
36. The task assistance device according to claim 32, further comprising a second update module configured to update the knowledge graph of competing objects based on the competing object information when the task process review file contains competing object information. ; Wherein, the competition objects include: at least one of institutional competition objects and product competition objects.
37. The task assisting device according to claim 30, further comprising:

    The investment strategy determination module is configured to obtain historical communication data of the target customer object, and determine the investment strategy of the target executive based on the historical communication data. The investment strategy includes at least one investment product and each investment product. recommended ratio.
38. The task assistance device according to claim 30, further comprising: a performance prediction robot module configured to:

    Based on the task process review file, predict the order probability of the target customer through the preset first machine learning model;

    According to the order probability of the target customer object, predict the achievement of the first cycle goal of the executive. The achievement of the first cycle goal includes whether the sales target of the first cycle is achieved and the sales performance of the first cycle. at least one of;

    Output the predicted goal achievement.
39. The task assisting device according to any one of claims 21-38, further comprising:

    a sales funnel robot module configured to track the target tasks of the executive to determine the customer stage in which the target customer object is;

    Based on the determined customer stage of the target customer object, update the actual conversion number of customer objects that the executive entered into each customer stage in the first cycle;

    The target conversion number and the actual conversion number of the customer objects that the executive entered into each customer stage in the first cycle are output according to a predetermined presentation method.
40. The task assisting device of claim 39, wherein the customer stages include a possible stage, a high potential stage and a converted stage.
41. An electronic device, the electronic device includes: a housing, a processor, a memory, a circuit board and a power circuit, wherein the electronic device The circuit board is placed inside the space enclosed by the casing, and the processor and memory are placed on the circuit board; the power circuit is used to supply power to each circuit or device of the above-mentioned electronic equipment; the memory is used to store executable program code; the processor passes The executable program code stored in the memory is read to run a program corresponding to the executable program code, for executing the method described in any one of claims 1-20.
42. A computer-readable storage medium that stores one or more programs, and the one or more programs can be executed by one or more processors to implement any one of claims 1-20 method described in the item.