80results about How to "Fit the actual needs" patented technology

The invention discloses a method of recommending clothing matching of a user based on a mobile terminal and the mobile terminal. The method of recommending user clothing matching based on the mobile terminal comprises the steps of receiving a clothing matching request of a user by the mobile terminal; obtaining existing position information, the weather information of the existing position and dressing style information of a city where the existing position is; obtaining pre-stored basic information of the user and a clothing photo of the user by combining the position information, the weather information and the dressing style information of the city; outputting a preset suite clothing matching scheme to the user. The clothing matching which is more fit for an actual demand of the user can be provided, and the living cost of the user can not be increased.

The invention discloses a resource adjusting method and device of an application service system. The method comprises, according to the parameter values of reserved resources which are collected in real time or periodically, determining whether to perform dilatation or shrinking adjustment; based on resource adjusting schemes in two directions, including a longitudinal resource adjusting scheme for increasing or reducing the resources on the basis of the inside of virtual machine systems and a transverse resource adjusting scheme for increasing or reducing the number of the virtual machine systems on the basis of application templates, preferably selecting a longitudinal dilatation direction during the dilatation, and preferably selecting a transverse reduction method during the reduction; according to a finally-determined increase or reduction direction, adjusting the resources of the application service system. According to the resource adjusting method and device of the application service system, resource allocation can be diversified in granularity, actual requirements and resource saving principles can be better met, and accordingly the resource utilization rate can be improved.

The invention discloses a load predicting method of a cloud data center. The method comprises steps of: acquiring historical data of the cloud data center and normalizing the historical data; computing correlation between CPU historical data and other performance indexes; extracting a time window; extracting features; fusing the features: splicing the acquired performance indexes and then inputting the spliced performance indexes into an own-coding neural network in order to further compress the spliced performance and finally obtain a common compression characteristic; performing manual intervention; performing supervised learning; and predicting a result. The method may discover a potential change signal so as to accurately grasp a change direction and get close to an actual demand. The method may increase prediction accuracy by 5 to 10 percent in practical application.

The present invention discloses an image evaluation method and device, a server and a storage medium. The method comprises the steps of: obtaining a feature set of an image, wherein the feature set comprises image subjective parameter features and/or image objective parameter features; and inputting the image feature set into a deep learning model which completes training, and obtaining an evaluation result of the image, wherein the deep learning model is obtained through training according to the feature set of a sample image and an evaluation result of the sample image. The accuracy of the image evaluation is improved to allow an evaluation result to better meet users' actual demands, and the technical problem is solved that a hit rate of a recommend image generated according to the evaluation result is low.

The invention relates to the technical field of software engineering, in particular relating to a method for searching Web services according to non-functional requirements of a user. The method comprises the following steps: processing a requirement text of the user, and extracting key words from the requirement text; using a noumenon to perform semantic disambiguation on the got key words; identifying the key words representing the non-functional requirements of the user, and mapping the key words to corresponding Web service quality attributes; collecting data of the quantity attributes tobe analyzed in the candidate Web services one by one, and using the cloud transform method to get a corresponding atomic concept set; transforming the got atomic concept set to a corresponding candidate concept set with appropriate grain size one by one; and selecting one concept which is most matched with the key words representing the non-functional requirements of the user from each of the sets respectively, and generating combined constraint conditions for inquiry according to a corresponding cloud model. By utilizing the qualitative and quantitative conversion of the cloud model, the impacts of subjective differences of experts and differences in environmental conditions on the inquiry are reduced, and a result which is closer to expectation of the user is returned.

The embodiment of the invention discloses an interaction control method and device of an intelligent blackboard, the intelligent blackboard and a storage medium, and relates to the field of intelligent blackboards. The intelligent blackboard comprises a touch module, at least one first blackboard area and at least one second blackboard area, wherein a display screen is installed in the first blackboard area, and the touch module is used for detecting touch operation for the first blackboard area and the second blackboard area. The method comprises the steps: receiving the first touch operationfor the second blackboard area; when the first touch operation is a writing operation, displaying a touch track corresponding to the writing operation in the display screen; when the first touch operation is a non-writing operation, responding according to a response strategy of the non-writing operation, and displaying a display picture corresponding to the non-writing operation in the display screen. By the adoption of the method, the technical problem that data interaction cannot be conducted between a traditional blackboard and electronic equipment in an intelligent blackboard in the prior art can be solved.

The invention provides a short text recommendation method and device, a medium and electronic equipment. The short text recommendation method comprises the following steps: acquiring a first short text input by a user; obtaining a plurality of second short texts in an ES mode, obtaining a semantic vector of the first short text and a semantic vector of each second short text, calculating the similarity between the semantic vector of each second short text and the semantic vector of the first short text, wherein the semantic vector of the short text is used for representing the feature vector of the short text semantics; and finally sorting the plurality of second short texts according to the similarity between the semantic vector of each second short text and the semantic vector of the first short text, and recommending the sorted second short texts. According to the scheme, the short texts are recalled and sorted from the deep semantic level of the short texts, so that the actual requirements of users can be better met, and the click rate of recommended contents is effectively increased.

The invention provides a message push method, a server and a terminal and relates to the field of the terminal. Relative position information of a user can be determined according to a label of an access network of the terminal, and further personalized push information is provided for the user according to the relative position information of the user. An application server obtains label information of the access network of the terminal, wherein the label information is used for indicating a position attribute of the access network; the application server determines the relative position information of a position at which the terminal is currently located according to the label information of the access network, wherein the relative position information is used for indicating the attribute of the position at which the terminal is currently located; and the application server determines push content according to the relative position information and generates a push request message according to the push content, wherein the push request message carries the push content.

The embodiment of the invention relates to the technical field of automatic vending, and discloses a commodity recommendation method and device for a vending robot. The method comprises the steps of obtaining current user information, wherein the current user information at least comprises a facial image of a current user; identifying one or more user features according to the current user information; inputting the user characteristics into a commodity recommendation model to obtain recommendation indexes of commodities in the vending robot for the current user, and recommending the commodities to the current user at least according to the recommendation indexes; and updating the recommendation index according to the condition that the current user purchases the recommended commodity andthe condition that the recommended commodity information is checked. Through the above mode, the commodity recommendation effect of the embodiment of the invention is good.

The application relates to an image processing method and device, a storage medium and electronic equipment. The method includes the following steps: acquiring an image to be processed; detecting whether the image to be processed is a first image with a user preference mark, wherein the first image with the user preference mark is an image subjected to a first preset operation in a preset application; if yes, identifying the first image with the user preference mark to obtain an image category to which the first image belongs; and dividing the first image with the user preference mark into animage set corresponding to the image category to which the first image belongs. According to the image processing method and device, the storage medium and the electronic equipment, the effectivenessof image classification can be improved.

The invention relates to an image classifying method and device, electronic equipment and a computer readable storage medium. The method comprises the steps of obtaining a first-level human face whichsatisfies a preset condition from images according to the size of the area of the human face, and conducting human face identification on the first-level human face to obtain the human face type corresponding to the first-level human face; then obtaining a second-level human face in the images, and then conducting human face identification on the second-level human face to obtain the human face type corresponding to the second-level human face, wherein the second-level human face is the human face except the first-level human face in the images; finally, classifying the images into corresponding human face types according to the human face type corresponding to the first-level human face and the human face type corresponding to the second-level human face. The human face types obtained inthis way can be accurate, a large quantity of unimportant human face types cannot be generated, and the effectiveness of the classification result is improved, which better meets actual requirementsof a user. Finally, the images are classified into the corresponding human face types.

The invention provides an application management method, management device and mobile terminal. The application management method comprises the following steps: detecting whether the currently downloaded application meets the preset freezing conditions; and if the currently downloaded application meets the preset freezing conditions, freezing the currently downloaded application. Through the technical scheme provided by the invention, the currently downloaded application can be automatically frozen, freezing control is performed on the application at the source end instead of manual freezing of the installed application afterwards, thus the manual operation quantity is reduced, actual needs of a user are better met, and the using experience of the user is improved.

The embodiment of the invention discloses a page display control method and device, equipment and a storage medium. The method comprises the steps that in the process of displaying first content in a current page of a preset application program, a first preset control is displayed in the current page, wherein the first preset control is used for establishing a preset incidence relation between a first user and a second user in the preset application program, the first user comprises the user currently using the preset application program, and the second user comprises a user issuing the first content; and the display mode of the first preset control is changed based on the interaction operation of the first user on the first content. By the adoption of the technical scheme, the display modes of the control can be richer, and therefore page display can be controlled more reasonably.

The invention discloses a method and a device for making a user taste label and recommending a menu. The method comprises the following steps: acquiring the geographic position of a user, acquiring the taste preference of the user on the geographic position, binding the geographic position with the taste preference, and storing as the user taste label. The technical problem that in the prior art,the user experience effect is poor is solved.

The invention provides a mouse control method and application thereof, and the method comprises the steps: building a selection table P of an initial DPI value of a mouse, recognizing the type of a real-time program D0, responding to the mouse in real time, on a host, selecting a DPI value matched with the type of the program from the selection table P, and setting the DPI value as the initial DPI value of the mouse. According to the method, the mouse DPI values can be primarily selected according to the program types, the selection efficiency is high, the calculation amount can be remarkably reduced, and the primarily selected mouse DPI values which are relatively adaptive can be provided for different types of programs. After primary selection, the mouse DPI value is adjusted for the first time and more than one time of subsequent adjustment to complete adjustment of the mouse DPI value, so that the mouse DPI value can be further matched with a corresponding program type, and compared with the method of selecting the DPI value by adopting an optimal iteration algorithm and the like in the prior art, the calculation amount can be remarkably reduced, the workload of a host is reduced, and crash of the host or occupation of a large number of computing resources is avoided, and the adjustment duration is short.

The invention provides a self-service collection mode of map data. The method comprises the following steps: S1) giving navigators to several taxi driver for free; S2) during usage of the navigators,collecting data of the navigators by a server, and timely sorting and analyzing the data; S3) through sorting and analyzing on the data, and by comparing the data and the current data, recording a newaddress and a route by the server; and S4) providing the new route through the server. According to the invention, collection of the map data is more convenient and faster, and the self-service collection mode applies to practical requirement of people. The self-service collection mode takes a brand new business idea, helps a trade company to integrate resources, reduces operation cost, and is liked by people with high-quality service.